[title] w2v作为预训练使用&&OOV默认向量&&词向量归一化 #word2vec #norm_w2v

def padding_vector.py

def padding_vector(embedding):
    """
    添加OOV默认词向量
    :param embedding: 
    :return: 
    """
    alpha = 0.5 * (2.0 * np.random.random() - 1.0)
    curr_embed = (2.0 * np.random.random_sample([embedding.shape[1]]) - 1.0) * alpha
    return np.row_stack((embedding, curr_embed))

w2v_helper.py

def w2v_helper():
    w2v = KeyedVectors.load_word2vec_format(w2v_fpath, binary=True)
    embedding = w2v.vectors
    embedding_padded = padding_vector(embedding)
    embedding_norm = norm_embedding(embedding_padded)
    return embedding_norm

w2v_norm_embedding.py

def norm_embedding(embedding):
    """
    w2v 归一化
    :param embedding:
    :return:
    """
    sum = np.sqrt(np.sum(np.square(embedding), axis=1))
    embedding = embedding / sum.reshape((len(embedding), 1))
    return embedding