QnARecurAtteLatest3Atten.py 文件源码

def vectorizeData(xContext, xQuestion, xAnswerBeing, xAnswerEnd, word_index, context_maxlen, question_maxlen):
    '''Vectorize the words to their respective index and pad context to max context length and question to max question length.
       Answers vectors are padded to the max context length as well.
    '''
    X = []
    Xq = []
    YBegin = []
    YEnd = []
    for i in xrange(len(xContext)):
        x = [word_index[w] for w in xContext[i]]
        xq = [word_index[w] for w in xQuestion[i]]
        # map the first and last words of answer span to one-hot representations
        y_Begin =  np.zeros(len(xContext[i]))
        y_Begin[xAnswerBeing[i]] = 1
        y_End = np.zeros(len(xContext[i]))
        y_End[xAnswerEnd[i]] = 1
        X.append(x)
        Xq.append(xq)
        YBegin.append(y_Begin)
        YEnd.append(y_End)
    return pad_sequences(X, maxlen=context_maxlen, padding='post'), pad_sequences(Xq, maxlen=question_maxlen, padding='post'), pad_sequences(YBegin, maxlen=context_maxlen, padding='post'), pad_sequences(YEnd, maxlen=context_maxlen, padding='post')

# for validation dataset