private static Map<Integer, Alignment> readAlignments(String fileName) {
Map<Integer,Alignment> alignments = new HashMap<Integer, Alignment>();
try {
BufferedReader in = new BufferedReader(new FileReader(fileName));
while (in.ready()) {
String line = in.readLine();
String[] words = line.split("\\s+");
if (words.length != 4)
throw new RuntimeException("Bad alignment file "+fileName+", bad line was "+line);
Integer sentenceID = Integer.parseInt(words[0]);
Integer englishPosition = Integer.parseInt(words[1])-1;
Integer frenchPosition = Integer.parseInt(words[2])-1;
String type = words[3];
Alignment alignment = alignments.get(sentenceID);
if (alignment == null) {
alignment = new Alignment();
alignments.put(sentenceID, alignment);
}
alignment.addAlignment(englishPosition, frenchPosition, type.equals("S"));
}
} catch (IOException e) {
throw new RuntimeException(e);
}
return alignments;
}
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();
// Model 1 assumes all alignments are equally likely
// So we can just take the argMax of t(f|e) to get the englishMaxPosition
for (int frenchPosition = 0; frenchPosition < numFrenchWords; frenchPosition++) {
String f = frenchWords.get(frenchPosition);
int englishMaxPosition = -1;
double maxTranslationProb = translationProbs.getCount(f, NULL);
for (int englishPosition = 0; englishPosition < numEnglishWords; englishPosition++) {
String e = englishWords.get(englishPosition);
double translationProb = translationProbs.getCount(f, e);
if (translationProb > maxTranslationProb) {
maxTranslationProb = translationProb;
englishMaxPosition = englishPosition;
}
}
alignment.addAlignment(englishMaxPosition, frenchPosition, true);
}
return alignment;
}
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;
}
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 maxDice = 0;
for (int englishPosition = 0; englishPosition < numEnglishWords; englishPosition++) {
String e = englishWords.get(englishPosition);
double dice = getDiceCoefficient(f,e);
if (dice > maxDice) {
maxDice = dice;
englishMaxPosition = englishPosition;
}
}
alignment.addAlignment(englishMaxPosition, frenchPosition, true);
}
return alignment;
}
public Alignment alignSentencePair(SentencePair sentencePair) {
Alignment alignment = new Alignment();
int numFrenchWords = sentencePair.getFrenchWords().size();
int numEnglishWords = sentencePair.getEnglishWords().size();
for (int frenchPosition = 0; frenchPosition < numFrenchWords; frenchPosition++) {
int englishPosition = frenchPosition;
if (englishPosition >= numEnglishWords)
englishPosition = -1;
alignment.addAlignment(englishPosition, frenchPosition, true);
}
return alignment;
}