short_sentence_similarity.py 文件源码

def info_content(lookup_word):
    """
    Uses the Brown corpus available in NLTK to calculate a Laplace
    smoothed frequency distribution of words, then uses this information
    to compute the information content of the lookup_word.
    """
    global N
    if N == 0:
        # poor man's lazy evaluation
        for sent in brown.sents():
            for word in sent:
                word = word.lower()
                if not word in brown_freqs:
                    brown_freqs[word] = 0
                brown_freqs[word] = brown_freqs[word] + 1
                N = N + 1
    lookup_word = lookup_word.lower()
    n = 0 if not lookup_word in brown_freqs else brown_freqs[lookup_word]
    return 1.0 - (math.log(n + 1) / math.log(N + 1))