From bba4ff830c8722cdcaf29e36c1ff5821a912ae5d Mon Sep 17 00:00:00 2001 From: Chris Dyer Date: Thu, 17 Dec 2009 13:57:54 -0500 Subject: added non-pruning intersection and a CRF tagger - the linear-chain tagger is more of a proof of concept than a real tagger-- the context-free assumptions made in a number of places mean that the algorithms used may not be as efficient as they could be, but the model is as powerful as any CRF - it would be easy to add latent variables or semi-CRF support (or both!) - i've added a couple basic features that are often used for POS tagging - non-pruning intersection is useful for lexical word alignment models and the tagger - a sample POS tagger model will be committed later --- decoder/tagger.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 decoder/tagger.h (limited to 'decoder/tagger.h') diff --git a/decoder/tagger.h b/decoder/tagger.h new file mode 100644 index 00000000..900019f2 --- /dev/null +++ b/decoder/tagger.h @@ -0,0 +1,17 @@ +#ifndef _TAGGER_H_ +#define _TAGGER_H_ + +#include "translator.h" + +struct TaggerImpl; +struct Tagger : public Translator { + Tagger(const boost::program_options::variables_map& conf); + bool Translate(const std::string& input, + SentenceMetadata* smeta, + const std::vector& weights, + Hypergraph* forest); + private: + boost::shared_ptr pimpl_; +}; + +#endif -- cgit v1.2.3