short_sentence_similarity.py 文件源码

def hierarchy_dist(synset_1, synset_2):
    """
    Return a measure of depth in the ontology to model the fact that
    nodes closer to the root are broader and have less semantic similarity
    than nodes further away from the root.
    """
    h_dist = six.MAXSIZE
    if synset_1 is None or synset_2 is None:
        return h_dist
    if synset_1 == synset_2:
        # return the depth of one of synset_1 or synset_2
        h_dist = max([x[1] for x in synset_1.hypernym_distances()])
    else:
        # find the max depth of least common subsumer
        hypernyms_1 = {x[0]:x[1] for x in synset_1.hypernym_distances()}
        hypernyms_2 = {x[0]:x[1] for x in synset_2.hypernym_distances()}
        lcs_candidates = set(hypernyms_1.keys()).intersection(
            set(hypernyms_2.keys()))
        if len(lcs_candidates) > 0:
            lcs_dists = []
            for lcs_candidate in lcs_candidates:
                lcs_d1 = 0
                if lcs_candidate in hypernyms_1 :
                    lcs_d1 = hypernyms_1[lcs_candidate]
                lcs_d2 = 0
                if lcs_candidate in hypernyms_2:
                    lcs_d2 = hypernyms_2[lcs_candidate]
                lcs_dists.append(max([lcs_d1, lcs_d2]))
            h_dist = max(lcs_dists)
        else:
            h_dist = 0
    return ((math.exp(BETA * h_dist) - math.exp(-BETA * h_dist)) /
        (math.exp(BETA * h_dist) + math.exp(-BETA * h_dist)))