Esempio n. 1
0
  /**
   * 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
  }
Esempio n. 2
0
 public double totalMass() {
   return lm.totalCount();
 }