请问演示功能中，粗分功能是哪个api

songsh · February 17, 2021, 3:16am

请问演示功能https://hanlp.hankcs.com/ 中，粗分功能是文档哪个api, 我需要，感谢

hankcs · February 17, 2021, 3:56am

对应2.1中的"tok/coarse"，请参考文档。

from hanlp_restful import HanLPClient
HanLP = HanLPClient('https://www.hanlp.com/api', auth=None, language='zh') # auth不填则匿名，zh中文，mul多语种
doc = HanLP.parse('2021年HanLPv2.1为生产环境带来次世代最先进的多语种NLP技术作为拜年🎁🧧', tasks='tok/coarse')
print(doc)

{
  "tok/coarse": [
    ["2021年", "HanLPv2.1", "为", "生产环境", "带来", "次世代", "最", "先进", "的", "多语种", "NLP", "技术", "作为", "拜年", "🎁🧧"]
  ]
}

songsh · February 17, 2021, 8:55am

hankcs:

from hanlp_restful import HanLPClient
HanLP = HanLPClient('https://www.hanlp.com/api', auth=None, language='zh') # auth不填则匿名，zh中文，mul多语种
doc = HanLP.parse('2021年HanLPv2.1为生产环境带来次世代最先进的多语种NLP技术作为拜年🎁🧧', tasks='tok/coarse')
print(doc)

{
  "tok/coarse": [
    ["2021年", "HanLPv2.1", "为", "生产环境", "带来", "次世代", "最", "先进", "的", "多语种", "NLP", "技术", "作为", "拜年", "🎁🧧"]
  ]
}

HanLP = hanlp.load()
本地方法调用可以吗？怎么写

hankcs · February 17, 2021, 4:09pm

github.com

hankcs/HanLP/blob/master/plugins/hanlp_demo/hanlp_demo/zh/demo_mtl.py#L8


# -*- coding:utf-8 -*-
# Author: hankcs
# Date: 2020-12-31 13:51
import hanlp
from hanlp_common.document import Document
HanLP = hanlp.load(hanlp.pretrained.mtl.CLOSE_TOK_POS_NER_SRL_DEP_SDP_CON_ELECTRA_BASE_ZH)
doc: Document = 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。'])
print(doc)
doc.pretty_print()
# Specify which annotation to use
# doc.pretty_print(ner='ner/ontonotes', pos='pku')

通过指定tasks='tok/coarse'可以减少运算量，提高速度，详见文档：

songsh · February 18, 2021, 1:00am

初学者，文档没怎么看懂, MultiTaskLearning是怎么用的？

songsh · February 18, 2021, 2:39pm

是想要这个粗分。

Rmeng-vir · March 11, 2021, 7:50am

同问：java api中是哪个API呢

873101411 · March 11, 2021, 9:42am

设置task = "tok/coarse"即为粗分词语功能