# Use latest NLPIR/ICTCLAS for Chinese Word Segmentation

**URL:** <https://discuss.elastic.co/t/use-latest-nlpir-ictclas-for-chinese-word-segmentation/123396>\
**Category:** Elasticsearch\
**Created:** [March 10, 2018, 7:09pm UTC](https://discuss.elastic.co/t/use-latest-nlpir-ictclas-for-chinese-word-segmentation/123396 "2018-03-10T19:09:48Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![zoellner](https://avatars.discourse-cdn.com/v4/letter/z/e8c25b/32.png) [@zoellner](https://discuss.elastic.co/u/zoellner)\
**Post date:** [March 10, 2018, 7:09pm UTC](https://discuss.elastic.co/t/use-latest-nlpir-ictclas-for-chinese-word-segmentation/123396/1 "2018-03-10T19:09:48Z")

</div>

My understanding is that the Smart Chinese Analysis plugin (`analysis-smartcn`) uses the underlying Lucene plugin `org.apache.lucene.analysis.cn.smart` which, according to its documentation, is based on dictionary data from ICTCLAS1.0  
ICTCLAS has had many updates since. An updated Lucene plugin is available here: [https://github.com/NLPIR-team/nlpir-analysis-cn-ictclas](https://github.com/NLPIR-team/nlpir-analysis-cn-ictclas)

My question is: Is it possible to update the underlying Lucene plugin in a way that the analysis-smartcn plugin would benefit from the updated dictionaries?

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [March 10, 2018, 7:57pm UTC](https://discuss.elastic.co/t/use-latest-nlpir-ictclas-for-chinese-word-segmentation/123396/2 "2018-03-10T19:57:11Z")

</div>

I can't comment with authority on this area, but if no one else does then I'd recommend creating an issue on GitHub about this as it seems like a pretty good feature request 🙂

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [April 7, 2018, 7:57pm UTC](https://discuss.elastic.co/t/use-latest-nlpir-ictclas-for-chinese-word-segmentation/123396/3 "2018-04-07T19:57:18Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.