/**
* GT smoothing with least squares interpolation. This follows the procedure in Jurafsky and
* Martin sect. 4.5.3.
*/
public void smoothAndNormalize() {
Counter<Integer> cntCounter = new Counter<Integer>();
for (K tok : lm.keySet()) {
int cnt = (int) lm.getCount(tok);
cntCounter.incrementCount(cnt);
}
final double[] coeffs = runLogSpaceRegression(cntCounter);
UNK_PROB = cntCounter.getCount(1) / lm.totalCount();
for (K tok : lm.keySet()) {
double tokCnt = lm.getCount(tok);
if (tokCnt <= unkCutoff) // Treat as unknown
unkTokens.add(tok);
if (tokCnt <= kCutoff) { // Smooth
double cSmooth = katzEstimate(cntCounter, tokCnt, coeffs);
lm.setCount(tok, cSmooth);
}
}
// Normalize
// Counters.normalize(lm);
// MY COUNTER IS ALWAYS NORMALIZED AND AWESOME
}
public Counter<String> getLogScoreCounter(LocalTrigramContext localTrigramContext) {
int position = localTrigramContext.getPosition();
String word = localTrigramContext.getWords().get(position);
Counter<String> tagCounter = unknownWordTags;
if (wordsToTags.keySet().contains(word)) {
tagCounter = wordsToTags.getCounter(word);
}
Set<String> allowedFollowingTags =
allowedFollowingTags(
tagCounter.keySet(),
localTrigramContext.getPreviousPreviousTag(),
localTrigramContext.getPreviousTag());
Counter<String> logScoreCounter = new Counter<String>();
for (String tag : tagCounter.keySet()) {
double logScore = Math.log(tagCounter.getCount(tag));
if (!restrictTrigrams
|| allowedFollowingTags.isEmpty()
|| allowedFollowingTags.contains(tag)) logScoreCounter.setCount(tag, logScore);
}
return logScoreCounter;
}