short_sentence_similarity.py 文件源码

def length_dist(synset_1, synset_2):
    """
    Return a measure of the length of the shortest path in the semantic
    ontology (Wordnet in our case as well as the paper's) between two
    synsets.
    """
    l_dist = six.MAXSIZE
    if synset_1 is None or synset_2 is None:
        return 0.0
    if synset_1 == synset_2:
        # if synset_1 and synset_2 are the same synset return 0
        l_dist = 0.0
    else:
        wset_1 = set([str(x.name()) for x in synset_1.lemmas()])
        wset_2 = set([str(x.name()) for x in synset_2.lemmas()])
        if len(wset_1.intersection(wset_2)) > 0:
            # if synset_1 != synset_2 but there is word overlap, return 1.0
            l_dist = 1.0
        else:
            # just compute the shortest path between the two
            l_dist = synset_1.shortest_path_distance(synset_2)
            if l_dist is None:
                l_dist = 0.0
    # normalize path length to the range [0,1]
    return math.exp(-ALPHA * l_dist)