Difference between revisions of "Resources for Chinese"
Jump to navigation
Jump to search
| (2 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
==Tools== | ==Tools== | ||
===Free software=== | ===Free software=== | ||
| − | * [https://github.com/yzhang/rseg rseg] word segmentation | + | * [https://github.com/yzhang/rseg rseg] word segmentation; written in ruby (no compilation, no hard dependencies apart from ruby), comes with a model (MIT license) |
| − | * [http://code.google.com/p/duduplus/ DuDuPlus: a graph-based dependency parser for English and Chinese] ("Other Open Source" | + | * [https://code.google.com/p/ctbparser/ ctbparser] word segmentation, POS tagging, NER, dependency parsing, all using Conditional Random Fields; written in C++ (LGPL license) |
| + | * [http://www.cl.cam.ac.uk/~yz360/zpar.html ZPar] word segmentation, POS tagging, CFG/dep/CCG parsing of Chinese and English; written in C++ (GPL3 license) | ||
| + | * [http://code.google.com/p/duduplus/ DuDuPlus: a graph-based dependency parser for English and Chinese] ("Other Open Source" license?) | ||
| + | ** where is the source code? | ||
==Data== | ==Data== | ||
| + | ===Free software=== | ||
| + | * [http://corpora.heliohost.org/ HC Corpora] 1606811 lines of [http://en.wikipedia.org/wiki/Fair_use Fair Use] excerpts from news, blogs, twitter | ||
| + | |||
===Unknown license=== | ===Unknown license=== | ||
* [http://www.chinesecomputing.com Chinese Computing] | * [http://www.chinesecomputing.com Chinese Computing] | ||
Revision as of 10:05, 6 December 2012
Tools
Free software
- rseg word segmentation; written in ruby (no compilation, no hard dependencies apart from ruby), comes with a model (MIT license)
- ctbparser word segmentation, POS tagging, NER, dependency parsing, all using Conditional Random Fields; written in C++ (LGPL license)
- ZPar word segmentation, POS tagging, CFG/dep/CCG parsing of Chinese and English; written in C++ (GPL3 license)
- DuDuPlus: a graph-based dependency parser for English and Chinese ("Other Open Source" license?)
- where is the source code?
Data
Free software
- HC Corpora 1606811 lines of Fair Use excerpts from news, blogs, twitter