コード例 #1
0
void
LexicalReordering::
SetCache(TranslationOption& to) const
{
  if (to.GetLexReorderingScores(this)) return;
  // Scores were were set already (e.g., by sampling phrase table)

  if (m_table) {
    Phrase const& sphrase = to.GetInputPath().GetPhrase();
    Phrase const& tphrase = to.GetTargetPhrase();
    to.CacheLexReorderingScores(*this, this->GetProb(sphrase,tphrase));
  } else { // e.g. OOV with Mmsapt
    // Scores vals(GetNumScoreComponents(), 0);
    // to.CacheLexReorderingScores(*this, vals);
  }
}
コード例 #2
0
void DecodeStepGeneration::Process(const TranslationOption &inputPartialTranslOpt
                                   , const DecodeStep &decodeStep
                                   , PartialTranslOptColl &outputPartialTranslOptColl
                                   , TranslationOptionCollection * /* toc */
                                   , bool /*adhereTableLimit*/) const
{
  if (inputPartialTranslOpt.GetTargetPhrase().GetSize() == 0) {
    // word deletion

    TranslationOption *newTransOpt = new TranslationOption(inputPartialTranslOpt);
    outputPartialTranslOptColl.Add(newTransOpt);

    return;
  }

  // normal generation step
  const GenerationDictionary* generationDictionary  = decodeStep.GetGenerationDictionaryFeature();

  const Phrase &targetPhrase  = inputPartialTranslOpt.GetTargetPhrase();
  const InputPath &inputPath = inputPartialTranslOpt.GetInputPath();
  size_t targetLength         = targetPhrase.GetSize();

  // generation list for each word in phrase
  vector< WordList > wordListVector(targetLength);

  // create generation list
  int wordListVectorPos = 0;
  for (size_t currPos = 0 ; currPos < targetLength ; currPos++) { // going thorugh all words
    // generatable factors for this word to be put in wordList
    WordList &wordList = wordListVector[wordListVectorPos];
    const Word &word = targetPhrase.GetWord(currPos);

    // consult dictionary for possible generations for this word
    const OutputWordCollection *wordColl = generationDictionary->FindWord(word);

    if (wordColl == NULL) {
      // word not found in generation dictionary
      //toc->ProcessUnknownWord(sourceWordsRange.GetStartPos(), factorCollection);
      return; // can't be part of a phrase, special handling
    } else {
      // sort(*wordColl, CompareWordCollScore);
      OutputWordCollection::const_iterator iterWordColl;
      for (iterWordColl = wordColl->begin() ; iterWordColl != wordColl->end(); ++iterWordColl) {
        const Word &outputWord = (*iterWordColl).first;
        const ScoreComponentCollection& score = (*iterWordColl).second;
        // enter into word list generated factor(s) and its(their) score(s)
        wordList.push_back(WordPair(outputWord, score));
      }

      wordListVectorPos++; // done, next word
    }
  }

  // use generation list (wordList)
  // set up iterators (total number of expansions)
  size_t numIteration = 1;
  vector< WordListIterator >  wordListIterVector(targetLength);
  vector< const Word* >       mergeWords(targetLength);
  for (size_t currPos = 0 ; currPos < targetLength ; currPos++) {
    wordListIterVector[currPos] = wordListVector[currPos].begin();
    numIteration *= wordListVector[currPos].size();
  }

  // go thru each possible factor for each word & create hypothesis
  for (size_t currIter = 0 ; currIter < numIteration ; currIter++) {
    ScoreComponentCollection generationScore; // total score for this string of words

    // create vector of words with new factors for last phrase
    for (size_t currPos = 0 ; currPos < targetLength ; currPos++) {
      const WordPair &wordPair = *wordListIterVector[currPos];
      mergeWords[currPos] = &(wordPair.first);
      generationScore.PlusEquals(wordPair.second);
    }

    // merge with existing trans opt
    Phrase genPhrase( mergeWords);

    if (IsFilteringStep()) {
      if (!inputPartialTranslOpt.IsCompatible(genPhrase, m_conflictFactors))
        continue;
    }

    const TargetPhrase &inPhrase = inputPartialTranslOpt.GetTargetPhrase();
    TargetPhrase outPhrase(inPhrase);
    outPhrase.GetScoreBreakdown().PlusEquals(generationScore);

    outPhrase.MergeFactors(genPhrase, m_newOutputFactors);
    outPhrase.Evaluate(inputPath.GetPhrase(), m_featuresToApply);

    const WordsRange &sourceWordsRange = inputPartialTranslOpt.GetSourceWordsRange();

    TranslationOption *newTransOpt = new TranslationOption(sourceWordsRange, outPhrase);
    assert(newTransOpt);

    newTransOpt->SetInputPath(inputPath);

    outputPartialTranslOptColl.Add(newTransOpt);

    // increment iterators
    IncrementIterators(wordListIterVector, wordListVector);
  }
}
コード例 #3
0
void SparseReordering::CopyScores(
               const TranslationOption& currentOpt,
               const TranslationOption* previousOpt,
               const InputType& input,
               LexicalReorderingState::ReorderingType reoType,
               LexicalReorderingConfiguration::Direction direction,
               ScoreComponentCollection* scores) const 
{
  if (m_useBetween && direction == LexicalReorderingConfiguration::Backward &&
      (reoType == LexicalReorderingState::D || reoType == LexicalReorderingState::DL ||
        reoType == LexicalReorderingState::DR)) {
    size_t gapStart, gapEnd;
    //NB: Using a static cast for speed, but could be nasty if 
    //using non-sentence input
    const Sentence& sentence = static_cast<const Sentence&>(input);
    const WordsRange& currentRange = currentOpt.GetSourceWordsRange();
    if (previousOpt) {
      const WordsRange& previousRange = previousOpt->GetSourceWordsRange();
      if (previousRange < currentRange) {
        gapStart = previousRange.GetEndPos() + 1;
        gapEnd = currentRange.GetStartPos();
      } else {
        gapStart = currentRange.GetEndPos() + 1;
        gapEnd = previousRange.GetStartPos();
      }
    } else {
      //start of sentence
      gapStart = 0;
      gapEnd  = currentRange.GetStartPos();
    }
    assert(gapStart < gapEnd);
    for (size_t i = gapStart; i < gapEnd; ++i) {
        AddFeatures(SparseReorderingFeatureKey::Between,
           SparseReorderingFeatureKey::Source, sentence.GetWord(i),
          SparseReorderingFeatureKey::First, reoType, scores);
    }
  }
  //std::cerr << "SR " << topt << " " << reoType << " " << direction << std::endl;
  //phrase (backward)
  //stack (forward)
  SparseReorderingFeatureKey::Type type;
  if (direction == LexicalReorderingConfiguration::Forward) {
    if (!m_useStack) return;
    type = SparseReorderingFeatureKey::Stack;
  } else if (direction == LexicalReorderingConfiguration::Backward) {
    if (!m_usePhrase) return;
    type = SparseReorderingFeatureKey::Phrase;
  } else {
    //Shouldn't be called for bidirectional
    //keep compiler happy
    type = SparseReorderingFeatureKey::Phrase;
    assert(!"Shouldn't call CopyScores() with bidirectional direction");
  }
  const Phrase& sourcePhrase = currentOpt.GetInputPath().GetPhrase();
  AddFeatures(type, SparseReorderingFeatureKey::Source, sourcePhrase.GetWord(0),
    SparseReorderingFeatureKey::First, reoType, scores);
  AddFeatures(type, SparseReorderingFeatureKey::Source, sourcePhrase.GetWord(sourcePhrase.GetSize()-1), SparseReorderingFeatureKey::Last, reoType, scores);
  const Phrase& targetPhrase = currentOpt.GetTargetPhrase();   
  AddFeatures(type, SparseReorderingFeatureKey::Target, targetPhrase.GetWord(0),
    SparseReorderingFeatureKey::First, reoType, scores);
  AddFeatures(type, SparseReorderingFeatureKey::Target, targetPhrase.GetWord(targetPhrase.GetSize()-1), SparseReorderingFeatureKey::Last, reoType, scores);


}