generation_metrics.py 文件源码

def get_sentiment_sim(context_seqs, gen_seqs):
    '''return the cosine similarity between the sentiment scores of each context and corresponding generated sequence;
    the sentiment scores are given in spacy'''
    gen_seqs = check_seqs_format(gen_seqs)
    emotion_types = ['AFRAID', 'AMUSED', 'ANGRY', 'ANNOYED', 'DONT_CARE', 'HAPPY', 'INSPIRED', 'SAD']
    gen_sentiment_sim_scores = []
    for context_seq, gen_seqs_ in zip(context_seqs, gen_seqs):
        context_sentiment = lexicon_methods.emotional_valence(encoder(context_seq))
        context_sentiment = numpy.array([context_sentiment[emotion_type] for emotion_type in emotion_types]) + 1e-8 #add tiny number to avoid NaN when all scores are 0
        sentiment_sim_scores = []
        for gen_seq in gen_seqs_:
            gen_sentiment = lexicon_methods.emotional_valence(encoder(gen_seq))
            gen_sentiment = numpy.array([gen_sentiment[emotion_type] for emotion_type in emotion_types]) + 1e-8 #add tiny number to avoid NaN when all scores are 0
            sentiment_sim = 1 - cosine(context_sentiment, gen_sentiment)
            sentiment_sim_scores.append(sentiment_sim)
        gen_sentiment_sim_scores.append(sentiment_sim_scores)

    gen_sentiment_sim_scores = numpy.array(gen_sentiment_sim_scores)
    return {'sentiment_sim_scores': gen_sentiment_sim_scores, 'mean_sentiment_sim_scores': numpy.mean(gen_sentiment_sim_scores)}