ansj_seg

Ansj Chinese word segmentation

Help

• Development documents: version 3.x and before, version 5.x and after

summary

This is a java implementation of Chinese word segmentation based on n-Gram+CRF+HMM.

The word segmentation speed reaches about 2 million words per second (tested on mac air), and the accuracy can reach more than 96%.

Currently, functions such as Chinese word segmentation, Chinese name recognition, user-defined dictionaries, keyword extraction, automatic summarization, and keyword tagging have been implemented.

It can be applied to natural language processing and other aspects, and is suitable for various projects that require high word segmentation effects.

maven

        
        <dependency>
            <groupId>org.ansj</groupId>
            <artifactId>ansj_seg</artifactId>
            <version>5.1.1</version>
        </dependency>
    

Call demo

If you download for the first time and just want to test the test effect, you can call this simple interface

 String str = "欢迎使用ansj_seg,(ansj中文分词)在这里如果你遇到什么问题都可以联系我.我一定尽我所能.帮助大家.ansj_seg更快,更准,更自由!" ;
 System.out.println(ToAnalysis.parse(str));
 
 欢迎/v,使用/v,ansj/en,_,seg/en,,,(,ansj/en,中文/nz,分词/n,),在/p,这里/r,如果/c,你/r,遇到/v,什么/r,问题/n,都/d,可以/v,联系/v,我/r,./m,我/r,一定/d,尽我所能/l,./m,帮助/v,大家/r,./m,ansj/en,_,seg/en,更快/d,,,更/d,准/a,,,更/d,自由/a,!

Join Us

I have been thinking about it for a long time, no matter if anyone can help me. I'll write it down, if you're interested or enthusiastic, you can contact me.

• Supplementary documentation, adding calling examples and instructions
• Add some regular Recognition, for example, ID card number recognition, currently unfinished include时间识别, IP地址识别,邮箱识别,网址识别,词性识别, etc...
• Provide a more optimized CRF model. Replace ansj's default model.
• Supplementary test cases, incomplete testing in many places. If you are interested you can help!
• Reconstruct the name recognition model. Add models such as organization name recognition.
• Add syntax and grammar analysis
• Implement the word segmentation method of lstm
• Fill in the gaps...