paraphrase.py 文件源码

 复制代码def get_sils_matrix(method, scores, wordlist):
    ''' See get_sims_matrix for definitions, which are the same here. The
    difference is that the resulting matrix contains distances instead of
    similarities.

    :return: 2-dimensional np.ndarray of size len(wordlist) x len(wordlist)
    '''
    if method =='direct':
        sims = get_sims_matrix(method, scores, wordlist)
        sims = preprocessing.normalize(np.matrix(sims), norm='l2')
        sils = 1-sims
    elif method == 'dict_cosine': # cosine dist of word-PPDB2.0Score matrix
        sils = np.array([[dict_cosine_dist(scores.get(i,{}),scores.get(j,{})) for j in wordlist] for i in wordlist])
    elif method == 'dict_JS': # JS divergence of word-PPDB2.0Score matrix
        sils = np.array([[dict_js_divergence(scores.get(i,{}),scores.get(j,{}))[0] for j in wordlist] for i in wordlist])
    elif method == 'vec_cosine':
        d = scores.values()[0].shape[0]
        sils = np.array([[cosine(scores.get(i,np.zeros(d)), scores.get(j,np.zeros(d))) for j in wordlist] for i in wordlist])
    else:
        sys.stderr.write('Unknown sil method: %s' % method)
        return None
    sils = np.nan_to_num(sils)
    return sils