Пример #1
0
    private static List<Pair<String, Double>> convertCounter(Counter<String> counts, double power) {

      List<Pair<String, Double>> convertedCounts = new ArrayList<Pair<String, Double>>();

      for (String word : counts.keySet()) {
        double x = Math.pow(counts.getCount(word), power);
        Pair<String, Double> countPair = Pair.create(word, x);
        convertedCounts.add(countPair);
      }
      return convertedCounts;
    }
Пример #2
0
    private Pair<Integer, Set<Integer>> getWordContextPair(
        List<String> sentence, int wordPosition) {

      String centerWord = sentence.get(wordPosition);
      int centerWordIndex = encodedVocab.get(centerWord);
      Set<Integer> contextWordSet = new HashSet<Integer>();

      for (int i = wordPosition - contextSize; i < wordPosition + contextSize; i++) {
        if (i < 0) continue; // Ignore contexts prior to start of sentence
        if (i >= sentence.size()) break; // Ignore contexts after end of current sentence
        if (i == centerWordIndex) continue; // Ignore center word

        String contextWord = sentence.get(i);
        int contextWordIndex = encodedVocab.get(contextWord);
        contextWordSet.add(contextWordIndex);
      }
      return Pair.create(centerWordIndex, contextWordSet);
    }