如何从nltk pos_tag获取标签集？

Question

我正在尝试从 nltk pos_tag 获取完整标签，但我找不到使用 nltk 执行此操作的简单方法。例如，使用tagsets='universal'.

from nltk.tokenize import word_tokenize

def nltk_pos(text):

    token = word_tokenize(text)

    return (nltk.pos_tag(token)[0])[1]

nltk_pos('home')

output: 'NN'

expected output: 'NOUN'

Answer 1

我在为自己写的一篇论文做 NLP 分析时也遇到了同样的问题。我必须使用这样的映射函数：import nltkfrom nltk.tokenize import word_tokenizedef get_full_tag_pos(pos_tag):    tag_dict = {"J": "ADJ",                "N": "NOUN",                "V": "VERB",                "R": "ADV"}    # assuming pos_tag comes in as capital letters i.e. 'JJR' or 'NN'    return tag_dict.get(pos_tag[0], 'NOUN')# examplewords = word_tokenize(text)words_pos = nltk.pos_tag(words)full_tag_words_pos = [word_pos[0] + "/" + get_full_tag_pos(word_pos[1]) for word_pos in words_pos]