lexicalCache PhraseDictionaryMultiModelCounts::CacheLexicalStatistics( const Phrase &phraseS, const Phrase &phraseT, AlignVector &alignment, const vector<lexicalTable*> &tables, bool is_input )
{
//do all the necessary lexical table lookups and get counts, but don't apply weights yet
Word null;
if (is_input) {
null.CreateFromString(Input, m_input, "NULL", false);
} else {
null.CreateFromString(Output, m_output, "NULL", false);
}
lexicalCache ret;
// all target words have to be explained
for(size_t ti=0; ti<alignment.size(); ti++) {
const set< size_t > & srcIndices = alignment[ ti ];
Word t_word = phraseT.GetWord(ti);
vector<lexicalPair> ti_vector;
if (srcIndices.empty()) {
// explain unaligned word by NULL
vector<float> joint_count (m_numModels);
vector<float> marginals (m_numModels);
FillLexicalCountsJoint(null, t_word, joint_count, tables);
FillLexicalCountsMarginal(null, marginals, tables);
ti_vector.push_back(make_pair(joint_count, marginals));
} else {
for (set< size_t >::const_iterator si(srcIndices.begin()); si != srcIndices.end(); ++si) {
Word s_word = phraseS.GetWord(*si);
vector<float> joint_count (m_numModels);
vector<float> marginals (m_numModels);
FillLexicalCountsJoint(s_word, t_word, joint_count, tables);
FillLexicalCountsMarginal(s_word, marginals, tables);
ti_vector.push_back(make_pair(joint_count, marginals));
}
}
ret.push_back(ti_vector);
}
return ret;
}
std::vector<double> StationaryMarginals(const DblCubeHypermatrix& P) {
std::vector<double> st = Stationary(P);
int dim = P.dim();
std::vector<double> marginals(dim, 0.0);
for (int i = 0; i < st.size(); ++i) {
int marginal_ind = (i % dim);
marginals[marginal_ind] += st[i];
}
return marginals;
}
// get lexical probability for single word alignment pair
double PhraseDictionaryMultiModelCounts::GetLexicalProbability( Word &wordS, Word &wordT, const vector<lexicalTable*> &tables, vector<float> &multimodelweights ) const
{
vector<float> joint_count (m_numModels);
vector<float> marginals (m_numModels);
FillLexicalCountsJoint(wordS, wordT, joint_count, tables);
FillLexicalCountsMarginal(wordS, marginals, tables);
double lexProb = m_combineFunction(joint_count, marginals, multimodelweights);
return lexProb;
}
