/**
* 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 double getCount(K token) {
if (!lm.keySet().contains(token)) {
System.err.println(lm.keySet().size());
throw new RuntimeException("token not in keyset");
}
return lm.getCount(token);
}
private double[] runLogSpaceRegression(Counter<Integer> cntCounter) {
SimpleRegression reg = new SimpleRegression();
for (int cnt : cntCounter.keySet()) {
reg.addData(cnt, Math.log(cntCounter.getCount(cnt)));
}
// System.out.println(reg.getIntercept());
// System.out.println(reg.getSlope());
// System.out.println(regression.getSlopeStdErr());
double[] coeffs = new double[] {reg.getIntercept(), reg.getSlope()};
return coeffs;
}
public Set<K> getVocab() {
return Collections.unmodifiableSet(lm.keySet());
}
public int vocabSize() {
return lm.keySet().size();
}