hanlp

例子：

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

#!pip install hanlp

import hanlp
HanLP = hanlp.pipeline() \
    .append(hanlp.utils.rules.split_sentence, output_key='sentences') \
    .append(hanlp.load('FINE_ELECTRA_SMALL_ZH'), output_key='tok') \
    .append(hanlp.load('CTB9_POS_ELECTRA_SMALL'), output_key='pos') \
    .append(hanlp.load('MSRA_NER_ELECTRA_SMALL_ZH'), output_key='ner', input_key='tok') \
    .append(hanlp.load('CTB9_DEP_ELECTRA_SMALL', conll=0), output_key='dep', input_key='tok')\
    .append(hanlp.load('CTB9_CON_ELECTRA_SMALL'), output_key='con', input_key='tok')
ret = HanLP('2021年HanLPv2.1为生产环境带来次世代最先进的多语种NLP技术。阿婆主来到北京立方庭参观自然语义科技公司。')
ret

Building model … Moving model to GPUs [0] … Building model … Moving model to GPUs [0] … Building model … Moving model to GPUs [0] … Building model … Moving model to GPUs [0] … Building model … Moving model to GPUs [0] … #+begin_example {'sentences': ['2021 年 HanLPv2.1 为生产环境带来次世代最先进的多语种 NLP 技术。', '阿婆主来到北京立方庭参观自然语义科技公司。'], 'tok': [['2021 年', 'HanLPv2.1', '为', '生产', '环境', '带来', '次', '世代', '最', '先进', '的', '多', '语种', 'NLP', '技术', '。'], ['阿婆主', '来到', '北京', '立方庭', '参观', '自然', '语义', '科技', '公司', '。']], 'pos': [['NT', 'NR', 'P', 'NN', 'NN', 'VV', 'JJ', 'NN', 'AD', 'VA', 'DEC', 'CD', 'NN', 'NR', 'NN', 'PU'], ['NN', 'VV', 'NR', 'NR', 'VV', 'NN', 'NN', 'NN', 'NN', 'PU']], 'ner': [[('2021 年', 'DATE', 0, 1)], [('北京', 'ORGANIZATION', 2, 3), ('立方庭', 'LOCATION', 3, 4), ('自然语义科技公司', 'ORGANIZATION', 5, 9)]], 'dep': [[(6, 'tmod'), (6, 'nsubj'), (6, 'prep'), (5, 'nn'), (3, 'pobj'), (0, 'root'), (8, 'det'), (15, 'nn'), (10, 'advmod'), (15, 'rcmod'), (10, 'cpm'), (13, 'nummod'), (15, 'nn'), (15, 'nn'), (6, 'dobj'), (6, 'punct')], [(2, 'nsubj'), (0, 'root'), (4, 'nn'), (2, 'dobj'), (2, 'conj'), (9, 'nn'), (9, 'nn'), (9, 'nn'), (5, 'dobj'), (2, 'punct')]], 'con': 'TOP', [['IP', [['NP', [['_', ['2021 年']], ['NP', '_', ['HanLPv2.1']], ['VP', 'PP', [['_', ['为', ['NP', '_', ['生产', ['', ['环境']]]]]], ['VP', [['', ['带来']], ['NP', 'CP', [['CP', [['IP', [['VP', [['NP', [['DP', [['_', ['次']], ['NP', '_', ['世代']]]], ['ADVP', '_', ['最']], ['VP', '_', ['先进']]]]]], ['', ['的']]]]]], ['NP', [['ADJP', [['', ['多']]]], ['NP', '_', ['语种']]]], ['NP', '_', ['NLP', ['', ['技术']]]]]]]]]], ['', ['。']]]]]], ['TOP', 'IP', [['NP', [['_', ['阿婆主']], ['VP', 'VP', [['_', ['来到', ['NP', '_', ['北京', ['', ['立方庭']]]]]], ['VP', [['', ['参观']], ['NP', '_', ['自然', ['', ['语义']], ['', ['科技']], ['', ['公司']]]]]]]], ['', ['。']]]]]]]}

#+end_example