void ChartParser::Create(const WordsRange &wordsRange, ChartParserCallback &to)
{
assert(m_decodeGraphList.size() == m_ruleLookupManagers.size());
std::vector <DecodeGraph*>::const_iterator iterDecodeGraph;
std::vector <ChartRuleLookupManager*>::const_iterator iterRuleLookupManagers = m_ruleLookupManagers.begin();
for (iterDecodeGraph = m_decodeGraphList.begin(); iterDecodeGraph != m_decodeGraphList.end(); ++iterDecodeGraph, ++iterRuleLookupManagers) {
const DecodeGraph &decodeGraph = **iterDecodeGraph;
assert(decodeGraph.GetSize() == 1);
ChartRuleLookupManager &ruleLookupManager = **iterRuleLookupManagers;
size_t maxSpan = decodeGraph.GetMaxChartSpan();
if (maxSpan == 0 || wordsRange.GetNumWordsCovered() <= maxSpan) {
ruleLookupManager.GetChartRuleCollection(wordsRange, to);
}
}
if (wordsRange.GetNumWordsCovered() == 1 && wordsRange.GetStartPos() != 0 && wordsRange.GetStartPos() != m_source.GetSize()-1) {
bool alwaysCreateDirectTranslationOption = StaticData::Instance().IsAlwaysCreateDirectTranslationOption();
if (to.Empty() || alwaysCreateDirectTranslationOption) {
// create unknown words for 1 word coverage where we don't have any trans options
const Word &sourceWord = m_source.GetWord(wordsRange.GetStartPos());
m_unknown.Process(sourceWord, wordsRange, to);
}
}
}
float DistortionScoreProducer::CalculateDistortionScore(const Hypothesis& hypo,
const WordsRange &prev, const WordsRange &curr, const int FirstGap) const
{
if(!StaticData::Instance().UseEarlyDistortionCost()) {
return - (float) hypo.GetInput().ComputeDistortionDistance(prev, curr);
}
else {
/* Pay distortion score as soon as possible, from Moore and Quirk MT Summit 2007
Definitions:
S : current source range
S' : last translated source phrase range
S'' : longest fully-translated initial segment
*/
int prefixEndPos = (int)FirstGap-1;
if((int)FirstGap==-1)
prefixEndPos = -1;
// case1: S is adjacent to S'' => return 0
if ((int) curr.GetStartPos() == prefixEndPos+1) {
IFVERBOSE(4) std::cerr<< "MQ07disto:case1" << std::endl;
return 0;
}
// case2: S is to the left of S' => return 2(length(S))
if ((int) curr.GetEndPos() < (int) prev.GetEndPos()) {
IFVERBOSE(4) std::cerr<< "MQ07disto:case2" << std::endl;
return (float) -2*(int)curr.GetNumWordsCovered();
}
// case3: S' is a subsequence of S'' => return 2(nbWordBetween(S,S'')+length(S))
if ((int) prev.GetEndPos() <= prefixEndPos) {
IFVERBOSE(4) std::cerr<< "MQ07disto:case3" << std::endl;
int z = (int)curr.GetStartPos()-prefixEndPos - 1;
return (float) -2*(z + (int)curr.GetNumWordsCovered());
}
// case4: otherwise => return 2(nbWordBetween(S,S')+length(S))
IFVERBOSE(4) std::cerr<< "MQ07disto:case4" << std::endl;
return (float) -2*((int)curr.GetNumWordsBetween(prev) + (int)curr.GetNumWordsCovered());
}
}
Phrase Phrase::GetSubString(const WordsRange &wordsRange) const
{
Phrase retPhrase(wordsRange.GetNumWordsCovered());
for (size_t currPos = wordsRange.GetStartPos() ; currPos <= wordsRange.GetEndPos() ; currPos++) {
Word &word = retPhrase.AddWord();
word = GetWord(currPos);
}
return retPhrase;
}
Phrase Phrase::GetSubString(const WordsRange &wordsRange, FactorType factorType) const
{
Phrase retPhrase(wordsRange.GetNumWordsCovered());
for (size_t currPos = wordsRange.GetStartPos() ; currPos <= wordsRange.GetEndPos() ; currPos++) {
const Factor* f = GetFactor(currPos, factorType);
Word &word = retPhrase.AddWord();
word.SetFactor(factorType, f);
}
return retPhrase;
}
