private double getDiceCoefficient(String f, String e) {
double intersection = collocationCountSentences.getCount(f,e);
double cardinalityF = fCountSentences.getCount(f);
double cardinalityE = eCountSentences.getCount(e);
double dice = 2*intersection / (cardinalityF + cardinalityE);
return dice;
}
/** {@inheritDoc} */
@Override
public synchronized void incrAllCounters(AbstractCounters<Counter, CounterGroup> other) {
for (CounterGroup group : other) {
for (Counter counter : group) {
findCounter(group.getName(), counter.getName()).increment(counter.getValue());
}
}
}
public Alignment alignSentencePair(SentencePair sentencePair) {
Alignment alignment = new Alignment();
List<String> frenchWords = sentencePair.getFrenchWords();
List<String> englishWords = sentencePair.getEnglishWords();
int numFrenchWords = frenchWords.size();
int numEnglishWords = englishWords.size();
for (int frenchPosition = 0; frenchPosition < numFrenchWords; frenchPosition++) {
String f = frenchWords.get(frenchPosition);
int englishMaxPosition = frenchPosition;
if (englishMaxPosition >= numEnglishWords)
englishMaxPosition = -1; // map French word to BASELINE if c(f,e) = 0 for all English words
double maxConditionalProb = 0;
for (int englishPosition = 0; englishPosition < numEnglishWords; englishPosition++) {
String e = englishWords.get(englishPosition);
double conditionalGivenEnglish = collocationCounts.getCount(f, e) / (eCounts.getCount(e));
if (conditionalGivenEnglish > maxConditionalProb) {
maxConditionalProb = conditionalGivenEnglish;
englishMaxPosition = englishPosition;
}
}
alignment.addAlignment(englishMaxPosition, frenchPosition, true);
}
return alignment;
}
private void trainCounters() {
for (SentencePair sentencePair : trainingSentencePairs) {
List<String> frenchWords = sentencePair.getFrenchWords();
List<String> englishWords = sentencePair.getEnglishWords();
Set<String> frenchSet = new HashSet<String>(frenchWords);
Set<String> englishSet = new HashSet<String>(englishWords);
fCountSentences.incrementAll(frenchSet, 1.0);
eCountSentences.incrementAll(englishSet, 1.0);
for (String f: frenchSet) {
for (String e: englishSet)
collocationCountSentences.incrementCount(f, e, 1.0);
}
}
System.out.println("Trained!");
}
protected void addTag() {
// add tag for each stmt
Iterator it = iterator();
// int count = 0;
while (it.hasNext()) {
JPegStmt stmt = (JPegStmt) it.next();
int count = Counter.getTagNo();
// count++;
StringTag t = new StringTag(Integer.toString(count));
stmt.addTag(t);
}
}
private void trainCounters() {
for (SentencePair sentencePair : trainingSentencePairs) {
List<String> frenchWords = sentencePair.getFrenchWords();
List<String> englishWords = sentencePair.getEnglishWords();
//fCounts.incrementAll(frenchWords, 1.0); // won't affect the argMax
eCounts.incrementAll(englishWords, 1.0);
for (String f: frenchWords) {
for (String e: englishWords)
collocationCounts.incrementCount(f, e, 1.0);
}
}
System.out.println("Trained!");
}
private Duple<CrownOperations.Reason, ISynset> getEstimatedSynonym(
String targetLemma, Set<String> synonyms, POS pos, String gloss) {
Counter<ISynset> synsetCounts = new ObjectCounter<ISynset>();
List<String> lemmasInWn = new ArrayList<String>();
for (String lemma : synonyms) {
// Get the WordNet sysnet if it exists
Set<ISynset> senses = WordNetUtils.getSynsets(dict, lemma, pos);
if (senses.isEmpty()) continue;
lemmasInWn.add(lemma);
synsetCounts.countAll(senses);
// Get the hypernyms of the synset and count their occurrence too
for (ISynset synset : senses) {
// Do a sanity check that avoids attaching this Entry if its
// lemma appears anywhere near the synonoyms. This check
// potentially has some false positives since we might avoid
// putting the lemma somewhere valid (in which case it would
// have more than would valid location) but is used to avoid
// noisy integration
if (WordNetUtils.isAlreadyInWordNet(dict, targetLemma, pos, synset)) {
return null;
}
for (ISynsetID hyper : synset.getRelatedSynsets(Pointer.HYPERNYM)) {
ISynset hyperSyn = dict.getSynset(hyper);
if (WordNetUtils.isAlreadyInWordNet(dict, targetLemma, pos, hyperSyn)) {
return null;
}
synsetCounts.count(hyperSyn);
}
}
}
// Return null if we couldn't find any of the lemma's synonyms or
// hyponyms in WordNet
if (synsetCounts.items().isEmpty()) return null;
// If there was only one lemma in this list in WordNet, try comparing
// the glosses for just that word to find a match
if (lemmasInWn.size() == 1) {
double maxScore = 0;
ISynset best = null;
String bestGloss = null;
Set<ISynset> candidateSynonymSynsets = WordNetUtils.getSynsets(dict, lemmasInWn.get(0), pos);
for (ISynset candidate : candidateSynonymSynsets) {
String wnExtendedGloss = WordNetUtils.getGlossWithoutExamples(candidate);
double score = simFunc.compare(gloss, wnExtendedGloss);
if (maxScore < score) {
maxScore = score;
best = candidate;
bestGloss = wnExtendedGloss;
}
}
CrownOperations.Reason r = new CrownOperations.Reason(getClass());
r.set("relation_type", "synonym");
r.set("heuristic", "single-synonym");
r.set("max_score", maxScore);
return new Duple<CrownOperations.Reason, ISynset>(r, best);
} else {
// Check for whether there were ties in the max
ISynset mostFreq = synsetCounts.max();
int mostFreqCount = synsetCounts.getCount(mostFreq);
List<ISynset> ties = new ArrayList<ISynset>();
for (ISynset syn : synsetCounts.items()) {
int c = synsetCounts.getCount(syn);
if (c == mostFreqCount) ties.add(syn);
}
// If there was only one synset that had the maximum count, then we
// report this
if (ties.size() == 1) {
CrownOperations.Reason r = new CrownOperations.Reason(getClass());
r.set("relation_type", "synonym");
r.set("heuristic", "unambiguous-max");
r.set("count", mostFreqCount);
return new Duple<CrownOperations.Reason, ISynset>(r, mostFreq);
}
// Otherwise, we try breaking ties between the synsets using gloss
// similarity
else {
double maxScore = 0;
ISynset best = null;
String bestGloss = null;
for (ISynset candidate : ties) {
String wnExtendedGloss = WordNetUtils.getGlossWithoutExamples(candidate);
double score = simFunc.compare(gloss, wnExtendedGloss);
if (maxScore < score) {
maxScore = score;
best = candidate;
bestGloss = wnExtendedGloss;
}
}
CrownOperations.Reason r = new CrownOperations.Reason(getClass());
r.set("relation_type", "synonym");
r.set("heuristic", "tied-synonyms");
r.set("max_score", maxScore);
return new Duple<CrownOperations.Reason, ISynset>(r, best);
}
}
}
private CounterMap<String,String> trainEM(int maxIterations) {
Set<String> englishVocab = new HashSet<String>();
Set<String> frenchVocab = new HashSet<String>();
CounterMap<String,String> translations = new CounterMap<String,String>();
englishVocab.add(NULL);
int iteration = 0;
final double thresholdProb = 0.0001;
for (SentencePair sentencePair : trainingSentencePairs) {
List<String> frenchWords = sentencePair.getFrenchWords();
List<String> englishWords = sentencePair.getEnglishWords();
// add words from list to vocabulary sets
englishVocab.addAll(englishWords);
frenchVocab.addAll(frenchWords);
}
System.out.println("Ready");
// We need to initialize translations.getCount(f,e) uniformly
// t(f|e) summed over all e in {E + NULL} = 1
final double initialCount = 1.0 / englishVocab.size();
while(iteration < maxIterations) {
CounterMap<String,String> counts = new CounterMap<String,String>(); // set count(f|e) to 0 for all e,f
Counter<String> totalEnglish = new Counter<String>(); // set total(e) to 0 for all e
// E-step: loop over all sentences and update counts
for (SentencePair sentencePair : trainingSentencePairs) {
List<String> frenchWords = sentencePair.getFrenchWords();
List<String> englishWords = sentencePair.getEnglishWords();
int numFrenchWords = frenchWords.size();
int numEnglishWords = englishWords.size();
Counter<String> sTotalF = new Counter<String>();
// compute normalization constant sTotalF
for (int frenchPosition = 0; frenchPosition < numFrenchWords; frenchPosition++) {
String f = frenchWords.get(frenchPosition);
// initialize and compute for English = NULL
if (!translations.containsKey(f) && initialize)
translations.setCount(f, NULL, initialCount);
else if (!translations.containsKey(f))
translations.setCount(f, NULL, thresholdProb);
sTotalF.incrementCount(f, translations.getCount(f, NULL));
for (int englishPosition = 0; englishPosition < numEnglishWords; englishPosition++) {
String e = englishWords.get(englishPosition);
if (!(translations.getCounter(f)).containsKey(e) && initialize)
translations.setCount(f, e, initialCount);
else if (!(translations.getCounter(f)).containsKey(e))
translations.setCount(f, e, thresholdProb);
sTotalF.incrementCount(f, translations.getCount(f, e));
}
}
// collect counts in counts and totalEnglish
for (int frenchPosition = 0; frenchPosition < numFrenchWords; frenchPosition++) {
String f = frenchWords.get(frenchPosition);
// collect counts for English = NULL
double count = translations.getCount(f, NULL) / sTotalF.getCount(f);
counts.incrementCount(NULL, f, count);
totalEnglish.incrementCount(NULL, count);
for (int englishPosition = 0; englishPosition < numEnglishWords; englishPosition++) {
String e = englishWords.get(englishPosition);
count = translations.getCount(f, e) / sTotalF.getCount(f);
counts.incrementCount(e, f, count);
totalEnglish.incrementCount(e, count);
}
}
} // end of E-step
System.out.println("Completed E-step");
// M-step: update probabilities with counts from E-step and check for convergence
iteration++;
for (String e : counts.keySet()) {//englishVocab) {
double normalizer = totalEnglish.getCount(e);
for (String f : (counts.getCounter(e)).keySet()) {//frenchVocab) {
// To speed implementation, we want to update translations only when count / normalizer > threshold
double prob = counts.getCount(e, f) / normalizer;
if (!initialize) {
if (prob > thresholdProb)
translations.setCount(f, e, prob);
else
(translations.getCounter(f)).removeKey(e);
}
else {
translations.setCount(f, e, prob);
}
}
}
System.out.println("Completed iteration " + iteration);
} // end of M-step
System.out.println("Trained!");
return translations;
}