sentence.py 文件源码

def tag_sentences(sentences, pos_symbol=False):
    tokenized = []
    for sent in sentences:
        tokenized.append(tokenizer(sent))

    processed_list = tagger(tokenized)

    if not pos_symbol:
        output_list = []
        for sentence in processed_list:
            new_sentence = []
            for word in sentence:
                new_sentence.append((word[_IDX_WORD], POS_TAGS[word[_IDX_SYMBOL]]))
            output_list.append(new_sentence)
    else:
        output_list = processed_list

    return output_list