diff --git a/UD_any/data/feature_models/b0/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b0/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..033d2dd9266c408a98451d5b83c25dc79529e43c --- /dev/null +++ b/UD_any/data/feature_models/b0/lemmatizer_rules_incremental.fm @@ -0,0 +1,16 @@ +# FORM +b.0#FORM +# POS +b.0#POS +# MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 diff --git a/UD_any/data/feature_models/b0/morpho_incremental.fm b/UD_any/data/feature_models/b0/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..beca1d8990786a9386f821259c32af3324a387ab --- /dev/null +++ b/UD_any/data/feature_models/b0/morpho_incremental.fm @@ -0,0 +1,41 @@ +# FORM +b.0#FORM.fasttext +# POS +b.0#POS +# MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS diff --git a/UD_any/data/feature_models/b0/parser_nofuture.fm b/UD_any/data/feature_models/b0/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..024e113f5ab7e649ed94e53f8c2a247e6b3a10be --- /dev/null +++ b/UD_any/data/feature_models/b0/parser_nofuture.fm @@ -0,0 +1,98 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.0#POS +b.0.ldep#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b0/tagger_incremental.fm b/UD_any/data/feature_models/b0/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..e1f2841f7952b5f202b8eff83ccf30372352ced2 --- /dev/null +++ b/UD_any/data/feature_models/b0/tagger_incremental.fm @@ -0,0 +1,24 @@ +# FORM +b.0#FORM.fasttext +# POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b0/tokenizer_incremental.fm b/UD_any/data/feature_models/b0/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..0d674e861cd589e4831bf47ebd4b94bbe1b060b6 --- /dev/null +++ b/UD_any/data/feature_models/b0/tokenizer_incremental.fm @@ -0,0 +1,43 @@ +# FORM +b.0#FORM.fasttext +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.0#POS +# MORPHO +b.0#MORPHO diff --git a/UD_any/data/feature_models/b1/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b1/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..ab8cd8c7da6402bf67850bdff063b75976a1979a --- /dev/null +++ b/UD_any/data/feature_models/b1/lemmatizer_rules_incremental.fm @@ -0,0 +1,21 @@ +# FORM +b.-1#FORM +b.0#FORM +# POS +b.-1#POS +b.0#POS +# MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS diff --git a/UD_any/data/feature_models/b1/morpho_incremental.fm b/UD_any/data/feature_models/b1/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..79e26688d3fa04e3813779c94858b13d5bb1dc5a --- /dev/null +++ b/UD_any/data/feature_models/b1/morpho_incremental.fm @@ -0,0 +1,45 @@ +# FORM +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-1#POS +b.0#POS +# MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS diff --git a/UD_any/data/feature_models/b1/parser_nofuture.fm b/UD_any/data/feature_models/b1/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..f8fc04f0b348b1b562773a4a947cf5b5ce0f7775 --- /dev/null +++ b/UD_any/data/feature_models/b1/parser_nofuture.fm @@ -0,0 +1,106 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-1#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b1/tagger_incremental.fm b/UD_any/data/feature_models/b1/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..a1be9e9512b141ce2c7a89c3aae54bfdc5383b48 --- /dev/null +++ b/UD_any/data/feature_models/b1/tagger_incremental.fm @@ -0,0 +1,43 @@ +# FORM +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS diff --git a/UD_any/data/feature_models/b1/tokenizer_incremental.fm b/UD_any/data/feature_models/b1/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..d94534daf40d0eadbc1fb0045faeba545eb16f87 --- /dev/null +++ b/UD_any/data/feature_models/b1/tokenizer_incremental.fm @@ -0,0 +1,51 @@ +# FORM +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-1#POS +b.0#POS +# MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS diff --git a/UD_any/data/feature_models/b2/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b2/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..ef29bb6cc0f940c00d07788962a220f63829a3fe --- /dev/null +++ b/UD_any/data/feature_models/b2/lemmatizer_rules_incremental.fm @@ -0,0 +1,25 @@ +# FORM +b.-2#FORM +b.-1#FORM +b.0#FORM +# POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS +b.-2#EOS diff --git a/UD_any/data/feature_models/b2/morpho_incremental.fm b/UD_any/data/feature_models/b2/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..b9075f5f9874ee87353984d9ded2f82d57e13b18 --- /dev/null +++ b/UD_any/data/feature_models/b2/morpho_incremental.fm @@ -0,0 +1,49 @@ +# FORM +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS +b.-2#EOS diff --git a/UD_any/data/feature_models/b2/parser_nofuture.fm b/UD_any/data/feature_models/b2/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..ad23ea95343cf40f034e0245b094b35b4dc1a7f7 --- /dev/null +++ b/UD_any/data/feature_models/b2/parser_nofuture.fm @@ -0,0 +1,111 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-2#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-2#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-2#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-1#EOS +b.-2#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b2/tagger_incremental.fm b/UD_any/data/feature_models/b2/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..b8b748ff415d934c72e3e0c8c5a36cd61ea17cdf --- /dev/null +++ b/UD_any/data/feature_models/b2/tagger_incremental.fm @@ -0,0 +1,47 @@ +# FORM +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-2#POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-2#MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS +b.-2#EOS diff --git a/UD_any/data/feature_models/b2/tokenizer_incremental.fm b/UD_any/data/feature_models/b2/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..06d3e51adf239a481cfa6ad4180d54912dbd9167 --- /dev/null +++ b/UD_any/data/feature_models/b2/tokenizer_incremental.fm @@ -0,0 +1,55 @@ +# FORM +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS +b.-2#EOS diff --git a/UD_any/data/feature_models/b3/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b3/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..4ac2697eb1a7606649a2d0e15e5df0451742b6f9 --- /dev/null +++ b/UD_any/data/feature_models/b3/lemmatizer_rules_incremental.fm @@ -0,0 +1,29 @@ +# FORM +b.-3#FORM +b.-2#FORM +b.-1#FORM +b.0#FORM +# POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS diff --git a/UD_any/data/feature_models/b3/morpho_incremental.fm b/UD_any/data/feature_models/b3/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..025f20628eb2b6247e125471af0481dcb8432329 --- /dev/null +++ b/UD_any/data/feature_models/b3/morpho_incremental.fm @@ -0,0 +1,53 @@ +# FORM +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS diff --git a/UD_any/data/feature_models/b3/parser_nofuture.fm b/UD_any/data/feature_models/b3/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..a999d6110d997fefa1849407bbab6a3bea1d47f7 --- /dev/null +++ b/UD_any/data/feature_models/b3/parser_nofuture.fm @@ -0,0 +1,116 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-3#LEMMA.fasttext +b.-2#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-3#LABEL +b.-2#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-3#EOS +b.-2#EOS +b.-1#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b3/tagger_incremental.fm b/UD_any/data/feature_models/b3/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..a39eb9b16e6aec670804d79048b98410dccb297d --- /dev/null +++ b/UD_any/data/feature_models/b3/tagger_incremental.fm @@ -0,0 +1,51 @@ +# FORM +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-3#POS +b.-2#POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS diff --git a/UD_any/data/feature_models/b3/tokenizer_incremental.fm b/UD_any/data/feature_models/b3/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..b06646846105aa5061fff37ad10f333d103afc20 --- /dev/null +++ b/UD_any/data/feature_models/b3/tokenizer_incremental.fm @@ -0,0 +1,59 @@ +# FORM +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS diff --git a/UD_any/data/feature_models/b4/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b4/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..fd820ad5fc2654ae17745d35c465255c4996e590 --- /dev/null +++ b/UD_any/data/feature_models/b4/lemmatizer_rules_incremental.fm @@ -0,0 +1,30 @@ +# FORM +b.-1#FORM +b.0#FORM +# POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS diff --git a/UD_any/data/feature_models/b4/morpho_incremental.fm b/UD_any/data/feature_models/b4/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..951491cd1ecae4268ebaa48c04a92acb6e24a6e3 --- /dev/null +++ b/UD_any/data/feature_models/b4/morpho_incremental.fm @@ -0,0 +1,57 @@ +# FORM +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS diff --git a/UD_any/data/feature_models/b4/parser_nofuture.fm b/UD_any/data/feature_models/b4/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..7558417071877606240f3cb30a4f95aa595d8e2c --- /dev/null +++ b/UD_any/data/feature_models/b4/parser_nofuture.fm @@ -0,0 +1,121 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-4#LEMMA.fasttext +b.-3#LEMMA.fasttext +b.-2#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-4#LABEL +b.-3#LABEL +b.-2#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-4#EOS +b.-3#EOS +b.-2#EOS +b.-1#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b4/tagger_incremental.fm b/UD_any/data/feature_models/b4/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..f47593f064bfe975b0f71d6187d85b9d6c0352e0 --- /dev/null +++ b/UD_any/data/feature_models/b4/tagger_incremental.fm @@ -0,0 +1,55 @@ +# FORM +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS diff --git a/UD_any/data/feature_models/b4/tokenizer_incremental.fm b/UD_any/data/feature_models/b4/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..544af4f7a5124a40602dbf7dd4b22befe123eb86 --- /dev/null +++ b/UD_any/data/feature_models/b4/tokenizer_incremental.fm @@ -0,0 +1,63 @@ +# FORM +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS diff --git a/UD_any/data/feature_models/b5/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b5/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..0eabe0759a8e0a47177dc0852a01fb62114f8e5d --- /dev/null +++ b/UD_any/data/feature_models/b5/lemmatizer_rules_incremental.fm @@ -0,0 +1,33 @@ +# FORM +b.-1#FORM +b.0#FORM +# POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS diff --git a/UD_any/data/feature_models/b5/morpho_incremental.fm b/UD_any/data/feature_models/b5/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..c0d9513f9ff76eacf2520a12d00e9e3866359379 --- /dev/null +++ b/UD_any/data/feature_models/b5/morpho_incremental.fm @@ -0,0 +1,61 @@ +# FORM +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS diff --git a/UD_any/data/feature_models/b5/parser_nofuture.fm b/UD_any/data/feature_models/b5/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..1b9ba09aa9fd1fb4c3dee4ecb882962806d7f3f9 --- /dev/null +++ b/UD_any/data/feature_models/b5/parser_nofuture.fm @@ -0,0 +1,126 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-5#LEMMA.fasttext +b.-4#LEMMA.fasttext +b.-3#LEMMA.fasttext +b.-2#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-5#LABEL +b.-4#LABEL +b.-3#LABEL +b.-2#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-5#EOS +b.-4#EOS +b.-3#EOS +b.-2#EOS +b.-1#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b5/tagger_incremental.fm b/UD_any/data/feature_models/b5/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..47c3983b1383b18f8e9ae8f2af99ba74de495340 --- /dev/null +++ b/UD_any/data/feature_models/b5/tagger_incremental.fm @@ -0,0 +1,59 @@ +# FORM +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS diff --git a/UD_any/data/feature_models/b5/tokenizer_incremental.fm b/UD_any/data/feature_models/b5/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..48e481691b73d4ddec44d7fa38a04bace5996760 --- /dev/null +++ b/UD_any/data/feature_models/b5/tokenizer_incremental.fm @@ -0,0 +1,67 @@ +# FORM +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS diff --git a/UD_any/data/feature_models/b6/lemmatizer_rules_incremental.fm b/UD_any/data/feature_models/b6/lemmatizer_rules_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..e13a591dca85ed3e5f0dd0cd5cd55f2efc3d18fa --- /dev/null +++ b/UD_any/data/feature_models/b6/lemmatizer_rules_incremental.fm @@ -0,0 +1,36 @@ +# FORM +b.-1#FORM +b.0#FORM +# POS +b.-6#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-6#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# Suffixes +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# Prefixes +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS +b.-6#EOS diff --git a/UD_any/data/feature_models/b6/morpho_incremental.fm b/UD_any/data/feature_models/b6/morpho_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..89e491461f69cf2012aafa7dca0001a7a089b47e --- /dev/null +++ b/UD_any/data/feature_models/b6/morpho_incremental.fm @@ -0,0 +1,65 @@ +# FORM +b.-6#FORM.fasttext +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-6#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-6#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS +b.-6#EOS diff --git a/UD_any/data/feature_models/b6/parser_nofuture.fm b/UD_any/data/feature_models/b6/parser_nofuture.fm new file mode 100644 index 0000000000000000000000000000000000000000..8cab2b7e5a114342ab4d4bc7e9e41a0acb3e8d16 --- /dev/null +++ b/UD_any/data/feature_models/b6/parser_nofuture.fm @@ -0,0 +1,131 @@ +# LEMMA +s.0#LEMMA.fasttext +s.1#LEMMA.fasttext +s.2#LEMMA.fasttext +s.0.ldep#LEMMA.fasttext +s.1.ldep#LEMMA.fasttext +s.0.rdep#LEMMA.fasttext +s.1.rdep#LEMMA.fasttext +s.0.ldep.ldep#LEMMA.fasttext +s.1.ldep.ldep#LEMMA.fasttext +s.0.rdep.rdep#LEMMA.fasttext +s.1.rdep.rdep#LEMMA.fasttext +s.0.l2dep#LEMMA.fasttext +s.1.l2dep#LEMMA.fasttext +s.0.r2dep#LEMMA.fasttext +s.1.r2dep#LEMMA.fasttext +b.-6#LEMMA.fasttext +b.-5#LEMMA.fasttext +b.-4#LEMMA.fasttext +b.-3#LEMMA.fasttext +b.-2#LEMMA.fasttext +b.-1#LEMMA.fasttext +b.0#LEMMA.fasttext +b.0.ldep#LEMMA.fasttext +# POS +s.0#POS +s.1#POS +s.2#POS +s.0.ldep#POS +s.1.ldep#POS +s.0.rdep#POS +s.1.rdep#POS +s.0.ldep.ldep#POS +s.1.ldep.ldep#POS +s.0.rdep.rdep#POS +s.1.rdep.rdep#POS +s.0.l2dep#POS +s.1.l2dep#POS +s.0.r2dep#POS +s.1.r2dep#POS +b.-6#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +b.0.ldep#POS +b.-1.gov#POS +s.0.gov#POS +s.1.gov#POS +# MORPHO +s.0#MORPHO +s.1#MORPHO +s.2#MORPHO +s.0.ldep#MORPHO +s.1.ldep#MORPHO +s.0.rdep#MORPHO +s.1.rdep#MORPHO +s.0.ldep.ldep#MORPHO +s.1.ldep.ldep#MORPHO +s.0.rdep.rdep#MORPHO +s.1.rdep.rdep#MORPHO +s.0.l2dep#MORPHO +s.1.l2dep#MORPHO +s.0.r2dep#MORPHO +s.1.r2dep#MORPHO +b.-6#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +b.0.ldep#MORPHO +s.1.gov#MORPHO +b.-1.gov#MORPHO +s.0.gov#MORPHO +# LABELS +s.0.ldep#LABEL +s.1.ldep#LABEL +s.0.rdep#LABEL +s.1.rdep#LABEL +s.0.ldep.ldep#LABEL +s.1.ldep.ldep#LABEL +s.0.rdep.rdep#LABEL +s.1.rdep.rdep#LABEL +s.0.l2dep#LABEL +s.1.l2dep#LABEL +s.0.r2dep#LABEL +s.1.r2dep#LABEL +b.0.ldep#LABEL +b.-6#LABEL +b.-5#LABEL +b.-4#LABEL +b.-3#LABEL +b.-2#LABEL +b.-1#LABEL +b.0#LABEL +s.0#LABEL +s.1#LABEL +# DISTANCE +s.0#DIST.s.1 +b.0#DIST.s.0 +# VALENCY +s.0#nbr +s.1#nbr +s.0#nbl +s.1#nbl +# UPPERCASE +b.0#FORM.U +# EOS +b.-6#EOS +b.-5#EOS +b.-4#EOS +b.-3#EOS +b.-2#EOS +b.-1#EOS +# HISTORY +tc.0 +tc.1 +tc.2 +tc.3 +tc.4 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 diff --git a/UD_any/data/feature_models/b6/tagger_incremental.fm b/UD_any/data/feature_models/b6/tagger_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..43774cd1f3544a67bb166480ff4dba30375c2943 --- /dev/null +++ b/UD_any/data/feature_models/b6/tagger_incremental.fm @@ -0,0 +1,63 @@ +# FORM +b.-6#FORM.fasttext +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# POS +b.-6#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +# UPPERCASE +b.0#FORM.U +# LENGTH +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# MORPHO +b.-6#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS +b.-6#EOS diff --git a/UD_any/data/feature_models/b6/tokenizer_incremental.fm b/UD_any/data/feature_models/b6/tokenizer_incremental.fm new file mode 100644 index 0000000000000000000000000000000000000000..960b867a16eb2308f33a74c758ee8d651c0d9d8d --- /dev/null +++ b/UD_any/data/feature_models/b6/tokenizer_incremental.fm @@ -0,0 +1,71 @@ +# FORM +b.-6#FORM.fasttext +b.-5#FORM.fasttext +b.-4#FORM.fasttext +b.-3#FORM.fasttext +b.-2#FORM.fasttext +b.-1#FORM.fasttext +b.0#FORM.fasttext +# UPPERCASE +b.-1#FORM.U +# LENGTH +b.-1#FORM.LEN +b.0#FORM.LEN +# SUFFIXES +b.0#FORM.PART.-4.-4 +b.0#FORM.PART.-3.-3 +b.0#FORM.PART.-2.-2 +b.0#FORM.PART.-1.-1 +# PREFIXES +b.0#FORM.PART.0.0 +b.0#FORM.PART.1.1 +b.0#FORM.PART.2.2 +b.0#FORM.PART.3.3 +# RAW INPUT +raw.-5 +raw.-4 +raw.-3 +raw.-2 +raw.-1 +raw.0 +raw.2 +raw.3 +raw.4 +raw.5 +raw.6 +# Features methode incrementale +s.0#FORM.fasttext +s.0.ldep#FORM.fasttext +s.0#POS +s.0.ldep#POS +s.0#MORPHO +s.0.ldep#MORPHO +s.0.ldep.ldep#MORPHO +s.0.ldep#LABEL +s.0#DIST.s.1 +s.0#nbl +s.0#LABEL +b.0#LABEL +# POS +b.-6#POS +b.-5#POS +b.-4#POS +b.-3#POS +b.-2#POS +b.-1#POS +b.0#POS +# MORPHO +b.-6#MORPHO +b.-5#MORPHO +b.-4#MORPHO +b.-3#MORPHO +b.-2#MORPHO +b.-1#MORPHO +b.0#MORPHO +# EOS +b.-1#EOS +b.-2#EOS +b.-3#EOS +b.-4#EOS +b.-5#EOS +b.-6#EOS diff --git a/UD_any/tokeparser_incremental_b0/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b0/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..fc9f9f5478dac79bbe2f55f5cc8be1bb926180a8 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b0/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b0/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b0/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b0/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..411db9f254d087070af45445a50d09485ed1f481 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b0/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/machine.tm b/UD_any/tokeparser_incremental_b0/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b0/morpho.cla b/UD_any/tokeparser_incremental_b0/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..a0bbaf6090e0d6555a02fe498bffc90f283fa1b2 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b0/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/normal.tm b/UD_any/tokeparser_incremental_b0/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b0/parser.cla b/UD_any/tokeparser_incremental_b0/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..f8f6f803234c011d00ce8caa6cdb5190f3eda134 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b0/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/segmenter.cla b/UD_any/tokeparser_incremental_b0/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..e93321f9dce537508f8c297b6f7dc3c269d44637 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b0/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/strategy.cla b/UD_any/tokeparser_incremental_b0/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b0/tagger.cla b/UD_any/tokeparser_incremental_b0/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..2926406bcd6e8ec84609c62814db15af9520a641 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b0/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b0/test.bd b/UD_any/tokeparser_incremental_b0/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b0/tokenizer.cla b/UD_any/tokeparser_incremental_b0/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..a574ffa0fd8b59cf2ec66d5279ab9c19f3a8b56d --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b0/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b0/tokeparser.dicts b/UD_any/tokeparser_incremental_b0/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b0/train.bd b/UD_any/tokeparser_incremental_b0/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b0/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b1/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b1/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..c42ed4f49c27acd06e856b20c9c10deb6a8903f2 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b1/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b1/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b1/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b1/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..13dfa3acea912e9cd4ea9e80e9d3d76db867d5bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b1/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/machine.tm b/UD_any/tokeparser_incremental_b1/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b1/morpho.cla b/UD_any/tokeparser_incremental_b1/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..5703ac34baa2c62efc92a05990940fd1c612e66d --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b1/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/normal.tm b/UD_any/tokeparser_incremental_b1/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b1/parser.cla b/UD_any/tokeparser_incremental_b1/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..591d4962d33153f29f880b51f20df10a080c0e6e --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b1/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/segmenter.cla b/UD_any/tokeparser_incremental_b1/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..963a0f05b88dc322b64038ee99a5d70bc742e563 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b1/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/strategy.cla b/UD_any/tokeparser_incremental_b1/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b1/tagger.cla b/UD_any/tokeparser_incremental_b1/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..519b9fd46353580924bb39213f7414226f13ecaa --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b1/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b1/test.bd b/UD_any/tokeparser_incremental_b1/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b1/tokenizer.cla b/UD_any/tokeparser_incremental_b1/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..65ba67dabc3a087047d06ea455582315fa63d4f2 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b1/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b1/tokeparser.dicts b/UD_any/tokeparser_incremental_b1/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b1/train.bd b/UD_any/tokeparser_incremental_b1/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b1/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b2/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b2/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..bb7f8f9a4a53c27d403d4ceaf60e80ce5c667433 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b2/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b2/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b2/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b2/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..5a953dab78a0af533de8cb0ff56e2e6500d7543c --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b2/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/machine.tm b/UD_any/tokeparser_incremental_b2/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b2/morpho.cla b/UD_any/tokeparser_incremental_b2/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..af62742f1c2b4bdfa0c7ce7af460b147110ad817 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b2/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/normal.tm b/UD_any/tokeparser_incremental_b2/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b2/parser.cla b/UD_any/tokeparser_incremental_b2/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..173e09a4626984f738df67508af54cdf31506a1e --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b2/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/segmenter.cla b/UD_any/tokeparser_incremental_b2/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..a230c5e0d6bd13b51cacaebdaabe1b3eb30e52de --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b2/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/strategy.cla b/UD_any/tokeparser_incremental_b2/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b2/tagger.cla b/UD_any/tokeparser_incremental_b2/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..2d0fda8779e71a0e6b788838a53df7f7103c5728 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b2/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b2/test.bd b/UD_any/tokeparser_incremental_b2/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b2/tokenizer.cla b/UD_any/tokeparser_incremental_b2/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..a32aeaff6a907ebac7d08d4f3f0ce23a200f778b --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b2/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b2/tokeparser.dicts b/UD_any/tokeparser_incremental_b2/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b2/train.bd b/UD_any/tokeparser_incremental_b2/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b2/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b3/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b3/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..9a05392dcefcf35020a888716d7186593f8e5853 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b3/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b3/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b3/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b3/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..59297b06d5849e25221d937c341f10505710b574 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b3/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/machine.tm b/UD_any/tokeparser_incremental_b3/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b3/morpho.cla b/UD_any/tokeparser_incremental_b3/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..edd7e6dae63b98c3a1a631f549016f801cf8ae0d --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b3/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/normal.tm b/UD_any/tokeparser_incremental_b3/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b3/parser.cla b/UD_any/tokeparser_incremental_b3/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..ec3ee962036991487f62390dc59efc8cc2359a3f --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b3/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/segmenter.cla b/UD_any/tokeparser_incremental_b3/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..f4f3830497fcb8ef6f6fb50db2b4155170360c08 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b3/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/strategy.cla b/UD_any/tokeparser_incremental_b3/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b3/tagger.cla b/UD_any/tokeparser_incremental_b3/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..ab1740f4bb2e95a7c9d40800cb7dab49756547f6 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b3/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b3/test.bd b/UD_any/tokeparser_incremental_b3/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b3/tokenizer.cla b/UD_any/tokeparser_incremental_b3/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..0cbf9962f0653e1d90df473c8eb2f92c2fd391ae --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b3/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b3/tokeparser.dicts b/UD_any/tokeparser_incremental_b3/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b3/train.bd b/UD_any/tokeparser_incremental_b3/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b3/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b4/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b4/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..9e053b4f671e7adafd5d4771268858ba4e539528 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b4/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b4/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b4/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b4/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..74cc521645bbd4fe1459c6f40f614a9d9f920ae4 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b4/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/machine.tm b/UD_any/tokeparser_incremental_b4/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b4/morpho.cla b/UD_any/tokeparser_incremental_b4/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..1e7a2e80734c68cdbe243933d32cd1de86bdfaa1 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b4/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/normal.tm b/UD_any/tokeparser_incremental_b4/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b4/parser.cla b/UD_any/tokeparser_incremental_b4/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..3c88628c229e8b783cd89f64303787a744af65fb --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b4/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/segmenter.cla b/UD_any/tokeparser_incremental_b4/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..f739a6e87135e3f45efef7937b2db83381a0eb8f --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b4/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/strategy.cla b/UD_any/tokeparser_incremental_b4/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b4/tagger.cla b/UD_any/tokeparser_incremental_b4/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..15da3fc548c922e11734e6da8ae9e1cd4dddb64d --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b4/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b4/test.bd b/UD_any/tokeparser_incremental_b4/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b4/tokenizer.cla b/UD_any/tokeparser_incremental_b4/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..83165a3ca81b50e740a1de539afe8fd95e20c927 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b4/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b4/tokeparser.dicts b/UD_any/tokeparser_incremental_b4/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b4/train.bd b/UD_any/tokeparser_incremental_b4/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b4/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b5/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b5/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..2514b8368de6d09dc58dac804aed8a509e5f0d97 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b5/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b5/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b5/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b5/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..cb1a731e2a97198c1e95c17769947644bcccb7b7 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b5/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/machine.tm b/UD_any/tokeparser_incremental_b5/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b5/morpho.cla b/UD_any/tokeparser_incremental_b5/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..0a3b89539e5f9785674dba20d823ceb06628b537 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b5/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/normal.tm b/UD_any/tokeparser_incremental_b5/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b5/parser.cla b/UD_any/tokeparser_incremental_b5/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..7031c27ac6c86252834ab927267afef17dfda9c2 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b5/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/segmenter.cla b/UD_any/tokeparser_incremental_b5/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..d31db82bcb083bce28705f16f0d7b891ddef2ad3 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b5/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/strategy.cla b/UD_any/tokeparser_incremental_b5/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b5/tagger.cla b/UD_any/tokeparser_incremental_b5/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..f14190dd92913605244854fc73eaef1884e1570b --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b5/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b5/test.bd b/UD_any/tokeparser_incremental_b5/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b5/tokenizer.cla b/UD_any/tokeparser_incremental_b5/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..535bb4e732c2593805bf09ec38b2c40fd319d8e9 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b5/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b5/tokeparser.dicts b/UD_any/tokeparser_incremental_b5/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b5/train.bd b/UD_any/tokeparser_incremental_b5/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b5/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0 diff --git a/UD_any/tokeparser_incremental_b6/lemmatizer_case.cla b/UD_any/tokeparser_incremental_b6/lemmatizer_case.cla new file mode 100644 index 0000000000000000000000000000000000000000..69d719e47c536146dcc3b1013593cf7e2b577a28 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/lemmatizer_case.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Case +Type : Prediction +Oracle : lemma_case +Feature Model : data/feature_models/b6/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_case.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/lemmatizer_lookup.cla b/UD_any/tokeparser_incremental_b6/lemmatizer_lookup.cla new file mode 100644 index 0000000000000000000000000000000000000000..41f63b2bdd7c6f77b01de9b737396b6302adf0cb --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/lemmatizer_lookup.cla @@ -0,0 +1,4 @@ +Name : Lemmatizer_Lookup +Type : Information +Oracle : lemma_lookup +Oracle Filename : data/maca_trans_lemmatizer_exceptions.fplm diff --git a/UD_any/tokeparser_incremental_b6/lemmatizer_rules.cla b/UD_any/tokeparser_incremental_b6/lemmatizer_rules.cla new file mode 100644 index 0000000000000000000000000000000000000000..b7c10e33d75020999e181cb4b0b6ffe2dbbde1ca --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/lemmatizer_rules.cla @@ -0,0 +1,7 @@ +Name : Lemmatizer_Rules +Type : Prediction +Oracle : lemma_rules +Feature Model : data/feature_models/b6/lemmatizer_rules_incremental.fm +Action Set : data/lemmatizer_rules.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/machine.tm b/UD_any/tokeparser_incremental_b6/machine.tm new file mode 100644 index 0000000000000000000000000000000000000000..f591178c203e6b19d86ed8fc136b8ec7c74a505e --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/machine.tm @@ -0,0 +1,39 @@ +Name : Tokenizer, Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tokeparser.dicts +%CLASSIFIERS +strategy strategy.cla +tokenizer tokenizer.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +segmenter segmenter.cla +%STATES +strategy strategy +tokenizer tokenizer +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +segmenter segmenter +%TRANSITIONS +strategy tokenizer MOVE tokenizer +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +strategy segmenter MOVE segmenter +tokenizer strategy * +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * +segmenter strategy * diff --git a/UD_any/tokeparser_incremental_b6/morpho.cla b/UD_any/tokeparser_incremental_b6/morpho.cla new file mode 100644 index 0000000000000000000000000000000000000000..ed5b4eacc13794123abe7e230f6a92a17b9aa92c --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/morpho.cla @@ -0,0 +1,7 @@ +Name : Morpho +Type : Prediction +Oracle : morpho +Feature Model : data/feature_models/b6/morpho_incremental.fm +Action Set : data/morpho_parts.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/normal.tm b/UD_any/tokeparser_incremental_b6/normal.tm new file mode 100644 index 0000000000000000000000000000000000000000..77ebff3a44bbe8eab9cff6ccad1442f5be33ad7e --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/normal.tm @@ -0,0 +1,31 @@ +Name : Tagger, Morpho, Lemmatizer and Parser Machine +Dicts : tagparser.dicts +%CLASSIFIERS +strategy strategy.cla +tagger tagger.cla +morpho morpho.cla +lemmatizer_lookup lemmatizer_lookup.cla +lemmatizer_rules lemmatizer_rules.cla +lemmatizer_case lemmatizer_case.cla +parser parser.cla +%STATES +strategy strategy +tagger tagger +morpho morpho +lemmatizer_lookup lemmatizer_lookup +lemmatizer_rules lemmatizer_rules +lemmatizer_case lemmatizer_case +parser parser +%TRANSITIONS +strategy tagger MOVE tagger +strategy morpho MOVE morpho +strategy lemmatizer_lookup MOVE lemmatizer_lookup +strategy lemmatizer_rules MOVE lemmatizer_rules +strategy lemmatizer_case MOVE lemmatizer_case +strategy parser MOVE parser +tagger strategy * +morpho strategy * +lemmatizer_lookup strategy * +lemmatizer_case strategy * +lemmatizer_rules strategy * +parser strategy * diff --git a/UD_any/tokeparser_incremental_b6/parser.cla b/UD_any/tokeparser_incremental_b6/parser.cla new file mode 100644 index 0000000000000000000000000000000000000000..cad4cb12f073f90c0e34e0037a6d4af73c533d56 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/parser.cla @@ -0,0 +1,7 @@ +Name : Parser +Type : Prediction +Oracle : parser +Feature Model : data/feature_models/b6/parser_nofuture.fm +Action Set : data/parser.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/segmenter.cla b/UD_any/tokeparser_incremental_b6/segmenter.cla new file mode 100644 index 0000000000000000000000000000000000000000..00b8eea6c9c01f3e1f281b5b71cc383489ce7b67 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/segmenter.cla @@ -0,0 +1,7 @@ +Name : Segmenter +Type : Prediction +Oracle : segmenter +Feature Model : data/feature_models/b6/parser_nofuture.fm +Action Set : data/segmenter.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/strategy.cla b/UD_any/tokeparser_incremental_b6/strategy.cla new file mode 100644 index 0000000000000000000000000000000000000000..fcf66b5327394529227bad9f0bad3829ec50e052 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/strategy.cla @@ -0,0 +1,4 @@ +Name : Strategy +Type : Information +Oracle : strategy_tokenizer,tagger,morpho,lemmatizer,parser +Oracle Filename : none diff --git a/UD_any/tokeparser_incremental_b6/tagger.cla b/UD_any/tokeparser_incremental_b6/tagger.cla new file mode 100644 index 0000000000000000000000000000000000000000..78d2ee230e32d0e53b6dd7720898919af3a375e7 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/tagger.cla @@ -0,0 +1,7 @@ +Name : Tagger +Type : Prediction +Oracle : tagger +Feature Model : data/feature_models/b6/tagger_incremental.fm +Action Set : data/tagger.as +Topology : (800,RELU,0.3) +Dynamic : yes diff --git a/UD_any/tokeparser_incremental_b6/test.bd b/UD_any/tokeparser_incremental_b6/test.bd new file mode 100644 index 0000000000000000000000000000000000000000..b2ef99610702da83ccf3870556882c973892fc30 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/test.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none Final 1 +1 FORM hyp form Final 1 +3 POS hyp pos Final 1 +4 XPOS hyp pos Final 1 +5 MORPHO hyp morpho Final 1 +2 LEMMA hyp form Final 1 +6 GOV hyp int Final 1 +7 LABEL hyp labels Final 1 +0 EOS hyp eos Final 0 diff --git a/UD_any/tokeparser_incremental_b6/tokenizer.cla b/UD_any/tokeparser_incremental_b6/tokenizer.cla new file mode 100644 index 0000000000000000000000000000000000000000..6cdfb92b050bec95ac54da50907be78f0a1f80a6 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/tokenizer.cla @@ -0,0 +1,7 @@ +Name : Tokenizer +Type : Prediction +Oracle : tokenizer +Feature Model : data/feature_models/b6/tokenizer_incremental.fm +Action Set : data/tokenizer.as +Topology : (800,RELU,0.3) +Dynamic : no diff --git a/UD_any/tokeparser_incremental_b6/tokeparser.dicts b/UD_any/tokeparser_incremental_b6/tokeparser.dicts new file mode 100644 index 0000000000000000000000000000000000000000..7378953c2c6765752cb56f0393aba9cc09602b15 --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/tokeparser.dicts @@ -0,0 +1,93 @@ +#Name Dimension Mode # +############################ +# TOKENIZER +Tokenizer_actions 18 Embeddings _ 200 +Tokenizer_bool 16 Embeddings _ 20 +Tokenizer_int 16 Embeddings _ 2000 +Tokenizer_eos 16 Embeddings _ 20 +Tokenizer_gov 16 Embeddings _ 100 +Tokenizer_pos 18 Embeddings _ 30 +Tokenizer_form 80 Embeddings _ 20 +Tokenizer_form.f 80 Embeddings _ 200000 +Tokenizer_lemma 80 Embeddings _ 20 +Tokenizer_letters 80 Embeddings _ 5000 +Tokenizer_labels 18 Embeddings _ 200 +Tokenizer_morpho 22 Embeddings _ 8000 +# TAGGER +Tagger_actions 18 Embeddings _ 200 +Tagger_bool 16 Embeddings _ 20 +Tagger_int 16 Embeddings _ 2000 +Tagger_eos 16 Embeddings _ 20 +Tagger_gov 16 Embeddings _ 100 +Tagger_pos 18 Embeddings _ 30 +Tagger_form 80 Embeddings _ 20 +Tagger_form.f 80 Embeddings _ 200000 +Tagger_lemma 80 Embeddings _ 20 +Tagger_letters 80 Embeddings _ 5000 +Tagger_labels 18 Embeddings _ 200 +Tagger_morpho 22 Embeddings _ 8000 +# MORPHO +Morpho_actions 18 Embeddings _ 200 +Morpho_bool 16 Embeddings _ 20 +Morpho_int 16 Embeddings _ 2000 +Morpho_eos 16 Embeddings _ 20 +Morpho_gov 16 Embeddings _ 100 +Morpho_pos 18 Embeddings _ 30 +Morpho_form 80 Embeddings _ 20 +Morpho_form.f 80 Embeddings _ 200000 +Morpho_lemma 80 Embeddings _ 20 +Morpho_letters 80 Embeddings _ 5000 +Morpho_labels 18 Embeddings _ 200 +Morpho_morpho 22 Embeddings _ 80000 +# LEMMATIZER_RULE +Lemmatizer_Rules_actions 18 Embeddings _ 2000 +Lemmatizer_Rules_bool 16 Embeddings _ 20 +Lemmatizer_Rules_int 16 Embeddings _ 2000 +Lemmatizer_Rules_eos 16 Embeddings _ 20 +Lemmatizer_Rules_gov 16 Embeddings _ 20 +Lemmatizer_Rules_pos 18 Embeddings _ 30 +Lemmatizer_Rules_form 80 Embeddings _ 300000 +Lemmatizer_Rules_form.f 80 Embeddings _ 20 +Lemmatizer_Rules_lemma 80 Embeddings _ 20 +Lemmatizer_Rules_letters 80 Embeddings _ 5000 +Lemmatizer_Rules_labels 18 Embeddings _ 20 +Lemmatizer_Rules_morpho 22 Embeddings _ 8000 +# LEMMATIZER_CASE +Lemmatizer_Case_actions 18 Embeddings _ 2000 +Lemmatizer_Case_bool 16 Embeddings _ 20 +Lemmatizer_Case_int 16 Embeddings _ 2000 +Lemmatizer_Case_eos 16 Embeddings _ 20 +Lemmatizer_Case_gov 16 Embeddings _ 20 +Lemmatizer_Case_pos 18 Embeddings _ 30 +Lemmatizer_Case_form 80 Embeddings _ 300000 +Lemmatizer_Case_form.f 80 Embeddings _ 20 +Lemmatizer_Case_lemma 80 Embeddings _ 20 +Lemmatizer_Case_letters 80 Embeddings _ 5000 +Lemmatizer_Case_labels 18 Embeddings _ 20 +Lemmatizer_Case_morpho 22 Embeddings _ 8000 +# PARSER +Parser_actions 18 Embeddings _ 200 +Parser_bool 16 Embeddings _ 20 +Parser_int 16 Embeddings _ 2000 +Parser_eos 16 Embeddings _ 20 +Parser_gov 16 Embeddings _ 100 +Parser_pos 18 Embeddings _ 30 +Parser_form 80 Embeddings _ 20 +Parser_form.f 80 Embeddings _ 200000 +Parser_lemma 80 Embeddings _ 20 +Parser_letters 80 Embeddings _ 5000 +Parser_labels 18 Embeddings _ 200 +Parser_morpho 22 Embeddings _ 8000 +# SEGMENTER +Segmenter_actions 18 Embeddings _ 200 +Segmenter_bool 16 Embeddings _ 20 +Segmenter_int 16 Embeddings _ 2000 +Segmenter_eos 16 Embeddings _ 20 +Segmenter_gov 16 Embeddings _ 100 +Segmenter_pos 18 Embeddings _ 30 +Segmenter_form 80 Embeddings _ 20 +Segmenter_form.f 80 Embeddings _ 200000 +Segmenter_lemma 80 Embeddings _ 20 +Segmenter_letters 80 Embeddings _ 5000 +Segmenter_labels 18 Embeddings _ 200 +Segmenter_morpho 22 Embeddings _ 8000 diff --git a/UD_any/tokeparser_incremental_b6/train.bd b/UD_any/tokeparser_incremental_b6/train.bd new file mode 100644 index 0000000000000000000000000000000000000000..963c311cf239f7a4dfc4e5649efd3a79648a14bc --- /dev/null +++ b/UD_any/tokeparser_incremental_b6/train.bd @@ -0,0 +1,11 @@ +#Index Name ref/hyp dict Policy Must print?# +################################################### +0 ID hyp none FromZero 1 +1 FORM hyp form FromZero 1 +3 POS hyp pos FromZero 1 +4 XPOS hyp pos FromZero 1 +5 MORPHO hyp morpho FromZero 1 +2 LEMMA hyp form FromZero 1 +6 GOV hyp int FromZero 1 +7 LABEL hyp labels FromZero 1 +0 EOS hyp eos FromZero 0