From 411ad2eb4a09ef04a7529bc1a178e83f624c6569 Mon Sep 17 00:00:00 2001 From: Patrick Simianer Date: Mon, 13 Jan 2014 17:15:24 +0100 Subject: Felix' https://github.com/felleh lexical word alignment features --- decoder/Makefile.am | 1 + decoder/cdec_ff.cc | 2 + decoder/ff_lexical.h | 128 ++++++++++++++++++++++ training/dtrain/examples/standard/cdec.ini | 3 +- training/dtrain/examples/standard/expected-output | 115 +++++++++---------- 5 files changed, 191 insertions(+), 58 deletions(-) create mode 100644 decoder/ff_lexical.h diff --git a/decoder/Makefile.am b/decoder/Makefile.am index b735756d..c0371081 100644 --- a/decoder/Makefile.am +++ b/decoder/Makefile.am @@ -48,6 +48,7 @@ libcdec_a_SOURCES = \ ff_external.h \ ff_factory.h \ ff_klm.h \ + ff_lexical.h \ ff_lm.h \ ff_ngrams.h \ ff_parse_match.h \ diff --git a/decoder/cdec_ff.cc b/decoder/cdec_ff.cc index b2541722..80b42d22 100644 --- a/decoder/cdec_ff.cc +++ b/decoder/cdec_ff.cc @@ -24,6 +24,7 @@ #include "ff_charset.h" #include "ff_wordset.h" #include "ff_external.h" +#include "ff_lexical.h" void register_feature_functions() { @@ -39,6 +40,7 @@ void register_feature_functions() { RegisterFF(); RegisterFF(); RegisterFF(); + RegisterFF(); //TODO: use for all features the new Register which requires static FF::usage(false,false) give name ff_registry.Register("SpanFeatures", new FFFactory()); diff --git a/decoder/ff_lexical.h b/decoder/ff_lexical.h new file mode 100644 index 00000000..21c85b27 --- /dev/null +++ b/decoder/ff_lexical.h @@ -0,0 +1,128 @@ +#ifndef FF_LEXICAL_H_ +#define FF_LEXICAL_H_ + +#include +#include +#include "trule.h" +#include "ff.h" +#include "hg.h" +#include "array2d.h" +#include "wordid.h" +#include +#include +#include + +#include "filelib.h" +#include "stringlib.h" +#include "sentence_metadata.h" +#include "lattice.h" +#include "fdict.h" +#include "verbose.h" +#include "tdict.h" +#include "hg.h" + +using namespace std; + +namespace { + string Escape(const string& x) { + string y = x; + for (int i = 0; i < y.size(); ++i) { + if (y[i] == '=') y[i]='_'; + if (y[i] == ';') y[i]='_'; + } + return y; + } +} + +class LexicalFeatures : public FeatureFunction { +public: + LexicalFeatures(const std::string& param) { + if (param.empty()) { + cerr << "LexicalFeatures: using T,D,I\n"; + T_ = true; I_ = true; D_ = true; + } else { + const vector argv = SplitOnWhitespace(param); + assert(argv.size() == 3); + T_ = (bool) atoi(argv[0].c_str()); + I_ = (bool) atoi(argv[1].c_str()); + D_ = (bool) atoi(argv[2].c_str()); + cerr << "T=" << T_ << " I=" << I_ << " D=" << D_ << endl; + } + }; + static std::string usage(bool p,bool d) { + return usage_helper("LexicalFeatures","[0/1 0/1 0/1]","Sparse lexical word translation indicator features. If arguments are supplied, specify like this: translations insertions deletions",p,d); + } +protected: + virtual void TraversalFeaturesImpl(const SentenceMetadata& smeta, + const HG::Edge& edge, + const std::vector& ant_contexts, + SparseVector* features, + SparseVector* estimated_features, + void* context) const; + virtual void PrepareForInput(const SentenceMetadata& smeta); +private: + mutable std::map > rule2feats_; + bool T_; + bool I_; + bool D_; +}; + +void LexicalFeatures::PrepareForInput(const SentenceMetadata& smeta) { + rule2feats_.clear(); // std::map > +} + +void LexicalFeatures::TraversalFeaturesImpl(const SentenceMetadata& smeta, + const HG::Edge& edge, + const std::vector& ant_contexts, + SparseVector* features, + SparseVector* estimated_features, + void* context) const { + + map >::iterator it = rule2feats_.find(edge.rule_.get()); + if (it == rule2feats_.end()) { + const TRule& rule = *edge.rule_; + it = rule2feats_.insert(make_pair(&rule, SparseVector())).first; + SparseVector& f = it->second; + std::vector sf(edge.rule_->FLength(),false); // stores if source tokens are visited by alignment points + std::vector se(edge.rule_->ELength(),false); // stores if target tokens are visited by alignment points + int fid = 0; + // translations + for (unsigned i=0;i 0) {// if not visited and is terminal + ostringstream os; + os << "LD:" << Escape(TD::Convert(rule.f_[i])); + fid = FD::Convert(os.str()); + if (fid <= 0) continue; + if (D_) + f.add_value(fid, 1.0); + } + } + // word insertions + for (unsigned i=0;i= 1) {// if not visited and is terminal + ostringstream os; + os << "LI:" << Escape(TD::Convert(rule.e_[i])); + fid = FD::Convert(os.str()); + if (fid <= 0) continue; + if (I_) + f.add_value(fid, 1.0); + } + } + } + (*features) += it->second; +} + + +#endif diff --git a/training/dtrain/examples/standard/cdec.ini b/training/dtrain/examples/standard/cdec.ini index 6cba9e1e..044ae2f5 100644 --- a/training/dtrain/examples/standard/cdec.ini +++ b/training/dtrain/examples/standard/cdec.ini @@ -21,7 +21,8 @@ feature_function=RuleIdentityFeatures feature_function=RuleSourceBigramFeatures feature_function=RuleTargetBigramFeatures feature_function=RuleShape -feature_function=RuleWordAlignmentFeatures +#feature_function=RuleWordAlignmentFeatures +feature_function=LexicalFeatures 1 1 1 #feature_function=SourceSpanSizeFeatures #feature_function=SourceWordPenalty #feature_function=SpanFeatures diff --git a/training/dtrain/examples/standard/expected-output b/training/dtrain/examples/standard/expected-output index fa831221..2460cfbb 100644 --- a/training/dtrain/examples/standard/expected-output +++ b/training/dtrain/examples/standard/expected-output @@ -4,7 +4,8 @@ Reading ./nc-wmt11.en.srilm.gz ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 **************************************************************************************************** Example feature: Shape_S00000_T00000 -Seeding random number sequence to 4138446869 +T=1 I=1 D=1 +Seeding random number sequence to 2327685089 dtrain Parameters: @@ -36,87 +37,87 @@ Iteration #1 of 3. . 10 Stopping after 10 input sentences. WEIGHTS - Glue = -80.3 - WordPenalty = -51.247 - LanguageModel = +282.46 - LanguageModel_OOV = -85.8 - PhraseModel_0 = -100.06 - PhraseModel_1 = -98.692 - PhraseModel_2 = -9.4958 - PhraseModel_3 = +18.535 - PhraseModel_4 = +62.35 - PhraseModel_5 = +7 - PhraseModel_6 = +31.4 - PassThrough = -126.5 + Glue = +6.9 + WordPenalty = -46.426 + LanguageModel = +535.12 + LanguageModel_OOV = -123.5 + PhraseModel_0 = -160.73 + PhraseModel_1 = -350.13 + PhraseModel_2 = -187.81 + PhraseModel_3 = +172.04 + PhraseModel_4 = +0.90108 + PhraseModel_5 = +21.6 + PhraseModel_6 = +67.2 + PassThrough = -149.7 --- - 1best avg score: 0.25631 (+0.25631) - 1best avg model score: -4843.6 (-4843.6) - avg # pairs: 744.4 + 1best avg score: 0.23327 (+0.23327) + 1best avg model score: -9084.9 (-9084.9) + avg # pairs: 780.7 avg # rank err: 0 (meaningless) avg # margin viol: 0 k-best loss imp: 100% - non0 feature count: 1274 + non0 feature count: 1389 avg list sz: 91.3 - avg f count: 143.72 -(time 0.4 min, 2.4 s/S) + avg f count: 146.2 +(time 0.37 min, 2.2 s/S) Iteration #2 of 3. . 10 WEIGHTS - Glue = -117.4 - WordPenalty = -99.584 - LanguageModel = +395.05 - LanguageModel_OOV = -136.8 - PhraseModel_0 = +40.614 - PhraseModel_1 = -123.29 - PhraseModel_2 = -152 - PhraseModel_3 = -161.13 - PhraseModel_4 = -76.379 - PhraseModel_5 = +39.1 - PhraseModel_6 = +137.7 - PassThrough = -162.1 + Glue = -43 + WordPenalty = -22.019 + LanguageModel = +591.53 + LanguageModel_OOV = -252.1 + PhraseModel_0 = -120.21 + PhraseModel_1 = -43.589 + PhraseModel_2 = +73.53 + PhraseModel_3 = +113.7 + PhraseModel_4 = -223.81 + PhraseModel_5 = +64 + PhraseModel_6 = +54.8 + PassThrough = -331.1 --- - 1best avg score: 0.26751 (+0.011198) - 1best avg model score: -10061 (-5216.9) - avg # pairs: 639.1 + 1best avg score: 0.29568 (+0.062413) + 1best avg model score: -15879 (-6794.1) + avg # pairs: 566.1 avg # rank err: 0 (meaningless) avg # margin viol: 0 k-best loss imp: 100% - non0 feature count: 1845 + non0 feature count: 1931 avg list sz: 91.3 - avg f count: 139.88 -(time 0.35 min, 2.1 s/S) + avg f count: 139.89 +(time 0.33 min, 2 s/S) Iteration #3 of 3. . 10 WEIGHTS - Glue = -101.1 - WordPenalty = -139.97 - LanguageModel = +327.98 - LanguageModel_OOV = -234.7 - PhraseModel_0 = -144.49 - PhraseModel_1 = -263.88 - PhraseModel_2 = -149.25 - PhraseModel_3 = -38.805 - PhraseModel_4 = +50.575 - PhraseModel_5 = -52.4 - PhraseModel_6 = +41.6 - PassThrough = -230.2 + Glue = -44.3 + WordPenalty = -131.85 + LanguageModel = +230.91 + LanguageModel_OOV = -285.4 + PhraseModel_0 = -194.27 + PhraseModel_1 = -294.83 + PhraseModel_2 = -92.043 + PhraseModel_3 = -140.24 + PhraseModel_4 = +85.613 + PhraseModel_5 = +238.1 + PhraseModel_6 = +158.7 + PassThrough = -359.6 --- - 1best avg score: 0.36222 (+0.094717) - 1best avg model score: -17416 (-7355.5) - avg # pairs: 661.2 + 1best avg score: 0.37375 (+0.078067) + 1best avg model score: -14519 (+1359.7) + avg # pairs: 545.4 avg # rank err: 0 (meaningless) avg # margin viol: 0 k-best loss imp: 100% - non0 feature count: 2163 + non0 feature count: 2218 avg list sz: 91.3 - avg f count: 132.53 -(time 0.33 min, 2 s/S) + avg f count: 137.77 +(time 0.35 min, 2.1 s/S) Writing weights file to '-' ... done --- -Best iteration: 3 [SCORE 'fixed_stupid_bleu'=0.36222]. -This took 1.0833 min. +Best iteration: 3 [SCORE 'fixed_stupid_bleu'=0.37375]. +This took 1.05 min. -- cgit v1.2.3