generation_metrics.py 文件源码

def get_word2vec_sim(context_seq, gen_seq):
    '''return the word2vec cosine similarity between the context and each generated sequence 
    (where the word2vec representation for a sequence is just the average of its word vectors)'''
    word_pairs = get_word_pairs(context_seq, gen_seq)
    if word_pairs:
        pair_scores = [similarity.word2vec(encoder(word1),encoder(word2)) for word1,word2 in word_pairs]
    else: #no word pairs between context and generated sequences (e.g. generated sequence might be punctuation only)
        pair_scores = [0]
    # assert(len(word_pairs) == len(pair_scores))
    word2vec_sim = numpy.mean(pair_scores)
    return word2vec_sim