From c371b42359c25a7d47dc89324be171f7b4fae3e7 Mon Sep 17 00:00:00 2001
From: Franck Dary <franck.dary@lis-lab.fr>
Date: Fri, 3 Jul 2020 17:32:16 +0200
Subject: [PATCH] updated machines
---
UD_any/templates/tokeparser_base/machine.rm | 41 ++++++++++-----------
UD_any/templates/tokeparser_incr/machine.rm | 40 +++++++++-----------
UD_any/templates/tokeparser_seq/machine.rm | 41 ++++++++++-----------
3 files changed, 56 insertions(+), 66 deletions(-)
diff --git a/UD_any/templates/tokeparser_base/machine.rm b/UD_any/templates/tokeparser_base/machine.rm
index e4cd45b..3de9ff2 100644
--- a/UD_any/templates/tokeparser_base/machine.rm
+++ b/UD_any/templates/tokeparser_base/machine.rm
@@ -1,28 +1,23 @@
-Name : Tokenizer, Tagger, Morpho and Parser Machine
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
Classifier : tokeparser
{
- Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_parts.ts parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
- LossMultiplier : {segmenter,3.0}
- Network type : Modular
- StateName : Out{1024}
- Context : Buffer{-3 -2 -1} Stack{} Columns{FORM} LSTM{1 1 0 1} In{64} Out{64}
- Context : Buffer{-3 -2 -1 0} Stack{1 0} Columns{UPOS} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{ID} NbElem{1} Buffer{-1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FORM} NbElem{13} Buffer{-1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FEATS} NbElem{13} Buffer{-1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{EOS} NbElem{1} Buffer{-1 0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{DEPREL} NbElem{1} Buffer{} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- DepthLayerTree : Columns{DEPREL} Buffer{} Stack{2 1 0} LayerSizes{3} LSTM{1 1 0.0 1} In{64} Out{64}
- History : NbElem{10} LSTM{1 1 0 1} In{64} Out{64}
- RawInput : Left{5} Right{5} LSTM{1 1 0.0 1} In{32} Out{32}
+ 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 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{}
+ 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 : 0.5
- MLP : {2048 0.3 2048 0.3}
- End
- Optimizer : Adam {0.0003 0.9 0.999 0.00000001 0.00002 true}
+ 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 HEAD DEPREL EOS
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
Strategy
{
Block : End{cannotMove}
@@ -32,8 +27,10 @@ Strategy
Block : End{cannotMove}
tagger tagger * 1
Block : End{cannotMove}
- morpho morpho NOTHING 1
- morpho morpho * 0
+ 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
diff --git a/UD_any/templates/tokeparser_incr/machine.rm b/UD_any/templates/tokeparser_incr/machine.rm
index 0afaf01..051f605 100644
--- a/UD_any/templates/tokeparser_incr/machine.rm
+++ b/UD_any/templates/tokeparser_incr/machine.rm
@@ -1,28 +1,23 @@
-Name : Tokenizer, Tagger, Morpho and Parser Machine
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
Classifier : tokeparser
{
- Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_parts.ts parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
- LossMultiplier : {segmenter,3.0}
- Network type : Modular
- StateName : Out{1024}
- Context : Buffer{-3 -2 -1} Stack{} Columns{FORM} LSTM{1 1 0 1} In{64} Out{64}
- Context : Buffer{-3 -2 -1 0} Stack{1 0} Columns{UPOS} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{ID} NbElem{1} Buffer{-2 -1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FORM} NbElem{13} Buffer{-1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FEATS} NbElem{13} Buffer{-1 0} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{EOS} NbElem{1} Buffer{-1} Stack{} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{DEPREL} NbElem{1} Buffer{} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- DepthLayerTree : Columns{DEPREL} Buffer{} Stack{2 1 0} LayerSizes{3} LSTM{1 1 0.0 1} In{64} Out{64}
- History : NbElem{10} LSTM{1 1 0 1} In{64} Out{64}
- RawInput : Left{5} Right{5} LSTM{1 1 0.0 1} In{32} Out{32}
+ 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 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{}
+ 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 : 0.5
- MLP : {2048 0.3 2048 0.3}
- End
- Optimizer : Adam {0.0003 0.9 0.999 0.00000001 0.00002 true}
+ 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 HEAD DEPREL EOS
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
Strategy
{
Block : End{cannotMove}
@@ -30,8 +25,9 @@ Strategy
tokenizer tagger SPLIT 0
tokenizer tokenizer * 0
tagger morpho * 0
- morpho parser NOTHING 0
- morpho 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
diff --git a/UD_any/templates/tokeparser_seq/machine.rm b/UD_any/templates/tokeparser_seq/machine.rm
index 47fb4df..dd7708f 100644
--- a/UD_any/templates/tokeparser_seq/machine.rm
+++ b/UD_any/templates/tokeparser_seq/machine.rm
@@ -1,28 +1,23 @@
-Name : Tokenizer, Tagger, Morpho and Parser Machine
+Name : Tokenizer, Tagger, Morpho, Lemmatizer, Parser and Segmenter Machine
Classifier : tokeparser
{
- Transitions : {tokenizer,data/tokenizer.ts tagger,data/tagger.ts morpho,data/morpho_parts.ts parser,data/parser_eager_rel_strict.ts segmenter,data/segmenter.ts}
- LossMultiplier : {segmenter,3.0}
- Network type : Modular
- StateName : Out{1024}
- Context : Buffer{-3 -2 -1 1 2} Stack{} Columns{FORM} LSTM{1 1 0 1} In{64} Out{64}
- Context : Buffer{-3 -2 -1 0 1 2} Stack{1 0} Columns{UPOS} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{ID} NbElem{1} Buffer{-1 0 1} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FORM} NbElem{13} Buffer{-1 0 1 2} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{FEATS} NbElem{13} Buffer{-1 0 1 2} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{EOS} NbElem{1} Buffer{-1 0} Stack{} LSTM{1 1 0 1} In{64} Out{64}
- Focused : Column{DEPREL} NbElem{1} Buffer{} Stack{2 1 0} LSTM{1 1 0 1} In{64} Out{64}
- DepthLayerTree : Columns{DEPREL} Buffer{} Stack{2 1 0} LayerSizes{3} LSTM{1 1 0.0 1} In{64} Out{64}
- History : NbElem{10} LSTM{1 1 0 1} In{64} Out{64}
- RawInput : Left{5} Right{5} LSTM{1 1 0.0 1} In{32} Out{32}
+ 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 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{}
+ 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 : 0.5
- MLP : {2048 0.3 2048 0.3}
- End
- Optimizer : Adam {0.0003 0.9 0.999 0.00000001 0.00002 true}
+ 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 HEAD DEPREL EOS
+Predictions : ID FORM UPOS FEATS LEMMA HEAD DEPREL EOS
Strategy
{
Block : End{cannotMove}
@@ -32,8 +27,10 @@ Strategy
Block : End{cannotMove}
tagger tagger * 1
Block : End{cannotMove}
- morpho morpho NOTHING 1
- morpho morpho * 0
+ 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
--
GitLab