private static Set<String> extractVocabulary(List<TaggedSentence> taggedSentences) {
Set<String> vocabulary = new HashSet<String>();
for (TaggedSentence taggedSentence : taggedSentences) {
List<String> words = taggedSentence.getWords();
vocabulary.addAll(words);
}
return vocabulary;
}
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;
}