Language Technology Platform
Project description
LTP 4
LTP(Language Technology Platform) 提供了一系列中文自然语言处理工具,用户可以使用这些工具对于中文文本进行分词、词性标注、句法分析等等工作。
If you use any source codes included in this toolkit in your work, please kindly cite the following paper. The bibtex are listed below:
@article{che2020n, title={N-LTP: A Open-source Neural Chinese Language Technology Platform with Pretrained Models}, author={Che, Wanxiang and Feng, Yunlong and Qin, Libo and Liu, Ting}, journal={arXiv preprint arXiv:2009.11616}, year={2020} }
快速使用
from ltp import LTP
ltp = LTP() # 默认加载 Small 模型
seg, hidden = ltp.seg(["他叫汤姆去拿外衣。"])
pos = ltp.pos(hidden)
ner = ltp.ner(hidden)
srl = ltp.srl(hidden)
dep = ltp.dep(hidden)
sdp = ltp.sdp(hidden)
Language Bindings
- C++
- Rust
- Java
- Python Rebinding
指标
模型 | 分词 | 词性 | 命名实体 | 语义角色 | 依存句法 | 语义依存 | 速度(句/S) |
---|---|---|---|---|---|---|---|
LTP 4.0 (Base) | 98.7 | 98.5 | 95.4 | 80.6 | 89.5 | 75.2 | 39.12 |
LTP 4.0 (Base1) | 99.22 | 98.73 | 96.39 | 79.28 | 89.57 | 76.57 | --.-- |
LTP 4.0 (Base2) | 99.18 | 98.69 | 95.97 | 79.49 | 90.19 | 76.62 | --.-- |
LTP 4.0 (Small) | 98.4 | 98.2 | 94.3 | 78.4 | 88.3 | 74.7 | 43.13 |
LTP 4.0 (Tiny) | 96.8 | 97.1 | 91.6 | 70.9 | 83.8 | 70.1 | 53.22 |
模型算法
- 分词: Electra Small1 + Linear
- 词性: Electra Small + Linear
- 命名实体: Electra Small + Relative Transformer2 + Linear
- 依存句法: Electra Small + BiAffine + Eisner3
- 语义依存: Electra Small + BiAffine
- 语义角色: Electra Small + BiAffine + CRF
构建 Wheel 包
python setup.py sdist bdist_wheel
python -m twine upload dist/*
作者信息
- 冯云龙 <<ylfeng@ir.hit.edu.cn>>
开源协议
- 语言技术平台面向国内外大学、中科院各研究所以及个人研究者免费开放源代码,但如上述机构和个人将该平台用于商业目的(如企业合作项目等)则需要付费。
- 除上述机构以外的企事业单位,如申请使用该平台,需付费。
- 凡涉及付费问题,请发邮件到 car@ir.hit.edu.cn 洽商。
- 如果您在 LTP 基础上发表论文或取得科研成果,请您在发表论文和申报成果时声明“使用了哈工大社会计算与信息检索研究中心研制的语言技术平台(LTP)”. 同时,发信给car@ir.hit.edu.cn,说明发表论文或申报成果的题目、出处等。
脚注
- 1:: Chinese-ELECTRA
- 2:: [TENER: Adapting Transformer Encoder for Named Entity Recognition](https://arxiv.org/abs/1911.04474)
- 3:: [A PyTorch implementation of "Deep Biaffine Attention for Neural Dependency Parsing"](https://github.com/yzhangcs/parser)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ltp-4.1.4.tar.gz
(58.4 kB
view hashes)
Built Distribution
ltp-4.1.4-py3-none-any.whl
(94.1 kB
view hashes)