From 3008ab4a353d6547bd17a3dc4a05dcc2e4d623ee Mon Sep 17 00:00:00 2001
From: Franck Dary <franck.dary@lis-lab.fr>
Date: Sat, 4 Jul 2020 16:33:17 +0200
Subject: [PATCH] Added machiens
---
.../templates/tokeparser_base_two/machine.rm | 52 +++++++++++++++++++
.../templates/tokeparser_incr_two/machine.rm | 48 +++++++++++++++++
.../templates/tokeparser_seq_two/machine.rm | 52 +++++++++++++++++++
3 files changed, 152 insertions(+)
create mode 100644 UD_any/templates/tokeparser_base_two/machine.rm
create mode 100644 UD_any/templates/tokeparser_incr_two/machine.rm
create mode 100644 UD_any/templates/tokeparser_seq_two/machine.rm
diff --git a/UD_any/templates/tokeparser_base_two/machine.rm b/UD_any/templates/tokeparser_base_two/machine.rm
new file mode 100644
index 0000000..7468c88
--- /dev/null
+++ b/UD_any/templates/tokeparser_base_two/machine.rm
@@ -0,0 +1,52 @@
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
+Classifier : tokelemmatizer
+{
+ Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_whole.ts lemmatizer_rules,data/lemmatizer_rules.ts lemmatizer_case,data/lemmatizer_case.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 0} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ Focused : Column{prefix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ Focused : Column{suffix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ RawInput : Left{5} Right{10} LSTM{1 1 0.0 1} In{32} Out{32}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ SplitTrans : LSTM{1 1 0.0 1} In{64} Out{64}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Classifier : parser
+{
+ Transitions : {parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 0} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Splitwords : data/splitwords.ts
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
+Strategy
+{
+ Block : End{cannotMove}
+ tokenizer tokenizer ENDWORD 1
+ tokenizer tokenizer SPLIT 1
+ tokenizer tokenizer * 0
+ Block : End{cannotMove}
+ tagger tagger * 1
+ Block : End{cannotMove}
+ morpho morpho * 1
+ Block : End{cannotMove}
+ lemmatizer_rules lemmatizer_case * 0
+ lemmatizer_case lemmatizer_rules * 1
+ Block : End{cannotMove}
+ parser segmenter eager_SHIFT 0
+ parser segmenter eager_RIGHT_rel 0
+ parser parser * 0
+ segmenter parser * 1
+}
diff --git a/UD_any/templates/tokeparser_incr_two/machine.rm b/UD_any/templates/tokeparser_incr_two/machine.rm
new file mode 100644
index 0000000..cfc2e58
--- /dev/null
+++ b/UD_any/templates/tokeparser_incr_two/machine.rm
@@ -0,0 +1,48 @@
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
+Classifier : tokelemmatizer
+{
+ Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_whole.ts lemmatizer_rules,data/lemmatizer_rules.ts lemmatizer_case,data/lemmatizer_case.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 0} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ Focused : Column{prefix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ Focused : Column{suffix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ RawInput : Left{5} Right{10} LSTM{1 1 0.0 1} In{32} Out{32}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ SplitTrans : LSTM{1 1 0.0 1} In{64} Out{64}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Classifier : parser
+{
+ Transitions : {parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 0} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Splitwords : data/splitwords.ts
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
+Strategy
+{
+ Block : End{cannotMove}
+ tokenizer tagger ENDWORD 0
+ tokenizer tagger SPLIT 0
+ tokenizer tokenizer * 0
+ tagger morpho * 0
+ morpho lemmatizer_rules * 0
+ lemmatizer_rules lemmatizer_case * 0
+ lemmatizer_case parser * 0
+ parser segmenter eager_SHIFT 0
+ parser segmenter eager_RIGHT_rel 0
+ parser parser * 0
+ segmenter tokenizer * 1
+}
diff --git a/UD_any/templates/tokeparser_seq_two/machine.rm b/UD_any/templates/tokeparser_seq_two/machine.rm
new file mode 100644
index 0000000..3ab1eb2
--- /dev/null
+++ b/UD_any/templates/tokeparser_seq_two/machine.rm
@@ -0,0 +1,52 @@
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
+Classifier : tokelemmatizer
+{
+ Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_whole.ts lemmatizer_rules,data/lemmatizer_rules.ts lemmatizer_case,data/lemmatizer_case.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 10} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 b.1 b.2 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 b.1 b.2 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ Focused : Column{prefix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ Focused : Column{suffix3:FORM} NbElem{3} Buffer{0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
+ RawInput : Left{5} Right{10} LSTM{1 1 0.0 1} In{32} Out{32}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ SplitTrans : LSTM{1 1 0.0 1} In{64} Out{64}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Classifier : parser
+{
+ Transitions : {parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
+ LossMultiplier : {}
+ Network type : Modular
+ Contextual : Window{-10 10} Columns{FORM} LSTM{1 1 0 1} In{64} Out{128} w2v{data/pretrained.w2v} Targets{b.-3 b.-2 b.-1 b.0 b.1 b.2 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1}
+ Context : Targets{b.-3 b.-2 b.-1 b.0 b.1 b.2 s.0 s.1 s.2 b.0.0 s.0.0 s.0.-1 s.1.0 s.1.-1 s.2.0 s.2.-1} Columns{EOS ID UPOS FEATS DEPREL} LSTM{1 1 0 1} In{64} Out{64} w2v{}
+ History : NbElem{10} LSTM{1 1 0 1} In{32} Out{32}
+ InputDropout : 0.3
+ MLP : {1600 0.3 1600 0.3}
+ End
+ Optimizer : Adagrad {0.01 0.000001 0 0.0000000001}
+}
+Splitwords : data/splitwords.ts
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
+Strategy
+{
+ Block : End{cannotMove}
+ tokenizer tokenizer ENDWORD 1
+ tokenizer tokenizer SPLIT 1
+ tokenizer tokenizer * 0
+ Block : End{cannotMove}
+ tagger tagger * 1
+ Block : End{cannotMove}
+ morpho morpho * 1
+ Block : End{cannotMove}
+ lemmatizer_rules lemmatizer_case * 0
+ lemmatizer_case lemmatizer_rules * 1
+ Block : End{cannotMove}
+ parser segmenter eager_SHIFT 0
+ parser segmenter eager_RIGHT_rel 0
+ parser parser * 0
+ segmenter parser * 1
+}
--
GitLab