sourceContentSelector.py 文件源码

def score(question, sentence):
    score = 0
    sentence = map(ps.stem, sentence)
    keywords = getKeywords(question)
    question = map(ps.stem, question)
    score += proximity(keywords, sentence)
    question_ngrams = count_ngrams(question, MAX_NGRAMS, True)
    sentence_ngrams = count_ngrams(sentence, MAX_NGRAMS, True)
    precision, recall = bleu_score(question_ngrams, len(question), sentence_ngrams, len(sentence), 5)
    f1 = (2*precision*recall)/(precision+recall)
    score += 2*f1
    return score

# Finds the shortest window in the targest sentence
# in which all keywords appear, and assigns a score.