https://github.com/yizhiru/thulac4j
Chinese Word Segmentation Tool, THULAC的Java实现.
https://github.com/yizhiru/thulac4j
chinese-word-segmentation thulac
Last synced: 5 months ago
JSON representation
Chinese Word Segmentation Tool, THULAC的Java实现.
- Host: GitHub
- URL: https://github.com/yizhiru/thulac4j
- Owner: yizhiru
- License: apache-2.0
- Created: 2017-03-03T01:00:21.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2021-04-12T06:10:51.000Z (about 5 years ago)
- Last Synced: 2025-08-07T20:25:37.407Z (10 months ago)
- Topics: chinese-word-segmentation, thulac
- Language: Java
- Size: 17.4 MB
- Stars: 84
- Watchers: 10
- Forks: 31
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-java - THULAC4j
README
# thulac4j
thulac4j是[THULAC](http://thulac.thunlp.org/)的高效Java 8实现，具有分词速度快、准、强的特点；支持
- 自定义词典
- 繁体转简体
- 停用词过滤
## 使用示例
在项目中使用thulac4j，添加依赖（请使用最新版本）：
```xml
io.github.yizhiru
thulac4j
3.1.2
```
thulac4j支持中文分词与词性标注，使用示例如下：
```java
String sentence = "滔滔的流水，向着波士顿湾无声逝去";
List words = Segmenter.segment(sentence);
// [滔滔, 的, 流水, ，, 向着, 波士顿湾, 无声, 逝去]
POSTagger pos = new POSTagger("models/model_c_model.bin", "models/model_c_dat.bin");
List words = pos.tagging(sentence);
// [滔滔/a, 的/u, 流水/n, ，/w, 向着/p, 波士顿湾/ns, 无声/v, 逝去/v]
```
模型数据较大，没有放在jar包与源码。训练模型下载及更多使用说明，请参看[Wiki](https://github.com/yizhiru/thulac4j/wiki).
最后感谢THUNLP实验室！