diff options
author | Patrick Simianer <p@simianer.de> | 2014-01-13 17:15:24 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2014-01-13 17:15:24 +0100 |
commit | 6b6a2d966a0d341fe5abee8b332a9d89f6c95bc4 (patch) | |
tree | 4bcb7831741648c5817f6da6d12724f6b5a724d4 /decoder | |
parent | b60df3ce6c1a509f52fb19703963caefcfc9859b (diff) |
Felix' https://github.com/felleh lexical word alignment features
Diffstat (limited to 'decoder')
-rw-r--r-- | decoder/Makefile.am | 1 | ||||
-rw-r--r-- | decoder/cdec_ff.cc | 2 | ||||
-rw-r--r-- | decoder/ff_lexical.h | 128 |
3 files changed, 131 insertions, 0 deletions
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<SourceWordPenalty>(); RegisterFF<ArityPenalty>(); RegisterFF<BLEUModel>(); + RegisterFF<LexicalFeatures>(); //TODO: use for all features the new Register which requires static FF::usage(false,false) give name ff_registry.Register("SpanFeatures", new FFFactory<SpanFeatures>()); 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 <vector> +#include <map> +#include "trule.h" +#include "ff.h" +#include "hg.h" +#include "array2d.h" +#include "wordid.h" +#include <sstream> +#include <cassert> +#include <cmath> + +#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<string> 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<const void*>& ant_contexts, + SparseVector<double>* features, + SparseVector<double>* estimated_features, + void* context) const; + virtual void PrepareForInput(const SentenceMetadata& smeta); +private: + mutable std::map<const TRule*, SparseVector<double> > rule2feats_; + bool T_; + bool I_; + bool D_; +}; + +void LexicalFeatures::PrepareForInput(const SentenceMetadata& smeta) { + rule2feats_.clear(); // std::map<const TRule*, SparseVector<double> > +} + +void LexicalFeatures::TraversalFeaturesImpl(const SentenceMetadata& smeta, + const HG::Edge& edge, + const std::vector<const void*>& ant_contexts, + SparseVector<double>* features, + SparseVector<double>* estimated_features, + void* context) const { + + map<const TRule*, SparseVector<double> >::iterator it = rule2feats_.find(edge.rule_.get()); + if (it == rule2feats_.end()) { + const TRule& rule = *edge.rule_; + it = rule2feats_.insert(make_pair(&rule, SparseVector<double>())).first; + SparseVector<double>& f = it->second; + std::vector<bool> sf(edge.rule_->FLength(),false); // stores if source tokens are visited by alignment points + std::vector<bool> se(edge.rule_->ELength(),false); // stores if target tokens are visited by alignment points + int fid = 0; + // translations + for (unsigned i=0;i<rule.a_.size();++i) { + const AlignmentPoint& ap = rule.a_[i]; + sf[ap.s_] = true; // mark index as seen + se[ap.t_] = true; // mark index as seen + ostringstream os; + os << "LT:" << Escape(TD::Convert(rule.f_[ap.s_])) << ":" << Escape(TD::Convert(rule.e_[ap.t_])); + fid = FD::Convert(os.str()); + if (fid <= 0) continue; + if (T_) + f.add_value(fid, 1.0); + } + // word deletions + for (unsigned i=0;i<sf.size();++i) { + if (!sf[i] && rule.f_[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<se.size();++i) { + if (!se[i] && rule.e_[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 |