mosesdecoder/moses/src/GenerationDictionary.h

98 lines
2.8 KiB
C
Raw Normal View History

// $Id$
/***********************************************************************
Moses - factored phrase-based language decoder
Copyright (C) 2006 University of Edinburgh
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
***********************************************************************/
#ifndef moses_GenerationDictionary_h
#define moses_GenerationDictionary_h
#include <list>
#include <map>
#include <vector>
#include "ScoreComponentCollection.h"
#include "Phrase.h"
#include "TypeDef.h"
#include "Dictionary.h"
#include "DecodeFeature.h"
namespace Moses
{
class FactorCollection;
typedef std::map < Word , ScoreComponentCollection > OutputWordCollection;
// 1st = output phrase
// 2nd = log probability (score)
/** Implementation of a generation table in a trie.
*/
class GenerationDictionary : public Dictionary, public DecodeFeature
{
typedef std::map<const Word* , OutputWordCollection, WordComparer> Collection;
protected:
Collection m_collection;
// 1st = source
// 2nd = target
std::string m_filePath;
public:
/** constructor.
* \param numFeatures number of score components, as specified in ini file
*/
GenerationDictionary(
size_t numFeatures,
ScoreIndexManager &scoreIndexManager,
const std::vector<FactorType> &input,
const std::vector<FactorType> &output);
virtual ~GenerationDictionary();
// returns Generate
DecodeType GetDecodeType() const
{
return Generate;
}
//! load data file
bool Load(const std::string &filePath, FactorDirection direction);
size_t GetNumScoreComponents() const;
std::string GetScoreProducerDescription() const;
std::string GetScoreProducerWeightShortName() const
{
return "g";
}
/** number of unique input entries in the generation table.
* NOT the number of lines in the generation table
*/
size_t GetSize() const
{
return m_collection.size();
}
/** returns a bag of output words, OutputWordCollection, for a particular input word.
* Or NULL if the input word isn't found. The search function used is the WordComparer functor
*/
const OutputWordCollection *FindWord(const Word &word) const;
Feature function overhaul. Each feature function is computed in one of three ways: 1) Stateless feature functions from the phrase table/generation table: these are computed when the TranslationOption is created. They become part of the ScoreBreakdown object contained in the TranslationOption and are added to the feature value vector when a hypothesis is extended. 2) Stateless feature functions that are computed during state exploration. Currently, only WordPenalty falls into this category, but these functions implement a method Evaluate which do does not receive a Hypothesis or any contextual information. 3) Stateful feature functions: these features receive the arc information (translation option), compute some value and then return some context information. The context information created by a particular feature function is passed back to it as the previous context when a hypothesis originating at the node where the previous edge terminates is created. States in the search space may be recombined if the context information is identical. The context information must be stored in an object implementing the FFState interface. TODO: 1) the command line interface / MERT interface needs to go to named parameters that are otherwise opaque 2) StatefulFeatureFunction's Evaluate method should just take a TranslationOption and a context object. It is not good that it takes a hypothesis, because then people may be tempted to access information about the "previous" hypothesis without "declaring" this dependency. 3) Future cost estimates should be handled using feature functions. All stateful feature functions need some kind of future cost estimate. 4) Philipp's poor-man's cube pruning is broken. git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@2087 1f5c12ca-751b-0410-a591-d2e778427230
2009-02-06 18:43:06 +03:00
virtual bool ComputeValueInTranslationOption() const;
};
}
#endif