void PhraseDictionaryALSuffixArray::InitializeForInput(InputType const& source)
{
// populate with rules for this sentence
long translationId = source.GetTranslationId();
string grammarFile = GetFilePath() + "/grammar." + SPrint(translationId) + ".gz";
std::auto_ptr<RuleTableLoader> loader =
RuleTableLoaderFactory::Create(grammarFile);
bool ret = loader->Load(m_input, m_output, grammarFile, m_tableLimit,
*this);
CHECK(ret);
}
void PhraseDictionaryALSuffixArray::InitializeForInput(InputType const& source)
{
// clear out rules for previous sentence
m_collection.Clear();
// populate with rules for this sentence
long translationId = source.GetTranslationId();
string grammarFile = GetFilePath() + "/grammar.out." + SPrint(translationId);
// data from file
InputFileStream inFile(grammarFile);
std::auto_ptr<RuleTableLoader> loader =
RuleTableLoaderFactory::Create(grammarFile);
bool ret = loader->Load(*m_input, *m_output, inFile, *m_weight, m_tableLimit,
*m_languageModels, m_wpProducer, *this);
CHECK(ret);
}
void CoveredReferenceFeature::EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore) const
{
long id = input.GetTranslationId();
boost::unordered_map<long, std::multiset<string> >::const_iterator refIt = m_refs.find(id);
multiset<string> wordsInPhrase = GetWordsInPhrase(targetPhrase);
multiset<string> covered;
set_intersection(wordsInPhrase.begin(), wordsInPhrase.end(),
refIt->second.begin(), refIt->second.end(),
inserter(covered, covered.begin()));
vector<float> scores;
scores.push_back(covered.size());
scoreBreakdown.Assign(this, scores);
estimatedFutureScore->Assign(this, scores);
}
void PhraseDictionaryFuzzyMatch::CleanUpAfterSentenceProcessing(const InputType &source)
{
m_collection.erase(source.GetTranslationId());
}
void PhraseDictionaryFuzzyMatch::InitializeForInput(InputType const& inputSentence)
{
char dirName[] = "/tmp/moses.XXXXXX";
char *temp = mkdtemp(dirName);
UTIL_THROW_IF2(temp == NULL,
"Couldn't create temporary directory " << dirName);
string dirNameStr(dirName);
string inFileName(dirNameStr + "/in");
ofstream inFile(inFileName.c_str());
for (size_t i = 1; i < inputSentence.GetSize() - 1; ++i) {
inFile << inputSentence.GetWord(i);
}
inFile << endl;
inFile.close();
long translationId = inputSentence.GetTranslationId();
string ptFileName = m_FuzzyMatchWrapper->Extract(translationId, dirNameStr);
// populate with rules for this sentence
PhraseDictionaryNodeMemory &rootNode = m_collection[translationId];
FormatType format = MosesFormat;
// data from file
InputFileStream inStream(ptFileName);
// copied from class LoaderStandard
PrintUserTime("Start loading fuzzy-match phrase model");
const StaticData &staticData = StaticData::Instance();
const std::string& factorDelimiter = staticData.GetFactorDelimiter();
string lineOrig;
size_t count = 0;
while(getline(inStream, lineOrig)) {
const string *line;
if (format == HieroFormat) { // reformat line
UTIL_THROW(util::Exception, "Cannot be Hiero format");
//line = ReformatHieroRule(lineOrig);
} else {
// do nothing to format of line
line = &lineOrig;
}
vector<string> tokens;
vector<float> scoreVector;
TokenizeMultiCharSeparator(tokens, *line , "|||" );
if (tokens.size() != 4 && tokens.size() != 5) {
stringstream strme;
strme << "Syntax error at " << ptFileName << ":" << count;
UserMessage::Add(strme.str());
abort();
}
const string &sourcePhraseString = tokens[0]
, &targetPhraseString = tokens[1]
, &scoreString = tokens[2]
, &alignString = tokens[3];
bool isLHSEmpty = (sourcePhraseString.find_first_not_of(" \t", 0) == string::npos);
if (isLHSEmpty && !staticData.IsWordDeletionEnabled()) {
TRACE_ERR( ptFileName << ":" << count << ": pt entry contains empty target, skipping\n");
continue;
}
Tokenize<float>(scoreVector, scoreString);
const size_t numScoreComponents = GetNumScoreComponents();
if (scoreVector.size() != numScoreComponents) {
stringstream strme;
strme << "Size of scoreVector != number (" << scoreVector.size() << "!="
<< numScoreComponents << ") of score components on line " << count;
UserMessage::Add(strme.str());
abort();
}
UTIL_THROW_IF2(scoreVector.size() != numScoreComponents,
"Number of scores incorrectly specified");
// parse source & find pt node
// constituent labels
Word *sourceLHS;
Word *targetLHS;
// source
Phrase sourcePhrase( 0);
sourcePhrase.CreateFromString(Input, m_input, sourcePhraseString, factorDelimiter, &sourceLHS);
// create target phrase obj
TargetPhrase *targetPhrase = new TargetPhrase();
targetPhrase->CreateFromString(Output, m_output, targetPhraseString, factorDelimiter, &targetLHS);
// rest of target phrase
targetPhrase->SetAlignmentInfo(alignString);
targetPhrase->SetTargetLHS(targetLHS);
//targetPhrase->SetDebugOutput(string("New Format pt ") + line);
// component score, for n-best output
std::transform(scoreVector.begin(),scoreVector.end(),scoreVector.begin(),TransformScore);
std::transform(scoreVector.begin(),scoreVector.end(),scoreVector.begin(),FloorScore);
targetPhrase->GetScoreBreakdown().Assign(this, scoreVector);
targetPhrase->Evaluate(sourcePhrase, GetFeaturesToApply());
TargetPhraseCollection &phraseColl = GetOrCreateTargetPhraseCollection(rootNode, sourcePhrase, *targetPhrase, sourceLHS);
phraseColl.Add(targetPhrase);
count++;
if (format == HieroFormat) { // reformat line
delete line;
} else {
// do nothing
}
}
// sort and prune each target phrase collection
SortAndPrune(rootNode);
//removedirectoryrecursively(dirName);
}
void PhraseDictionaryFuzzyMatch::CleanUp(const InputType &source)
{
m_collection.erase(source.GetTranslationId());
}