Introduction to ictclassharpictclas Word Segmentation System (9) dictionary Expansion
Introduction to sharpictclas word splitting system (8) Others
Introduction to sharpictclas word splitting system (7) optimumsegment
Introduction to sharpictclas Word Segmentation System (6) Segment
Introduction to sharpictclas System (5) NShortPath-2
Introduction to sharpictclas System (4) NShortPath-1
Introduction to sharpictclas word splitting system (3) dynamicarray
Introduction to sharpictclas Word Segmentation System (2) Initial Word Segmentation
Introduction to sharpictclas Word Segmentation System (1) Reading dictionary Library
Porting ICTCLAS to the C # Platform
ICTCLAS text splitting system code (2)
Tianshu-like ICTCLAS Word Segmentation System Code (1) Other Resources 1 Name: shootsearch Chinese Word Segmentation component (C # Open Source)
Http://gforge.osdn.net.cn/frs? Group_id = 96
Rating: a complete and available Chinese Word Segmentation component. It supports both Chinese and English, and digital hybrid recognition. Thanks to developers for sharing. The personal name is based on a simple "last name + name" recognition method, which is not reliable. Based on the forward maximum matching algorithm, the accuracy is not very high. In addition, the architecture and code quality of the entire component are relatively general. However, it is based on the current situation of domestic. NET developers. It is not easy to achieve this level and it is still open-source.
2 Name: Mini word divider (Java open source)
Address: http://sourceforge.net/projects/wordsegment/
Rating: it is just a demo and only considers "Chinese" splitting. However, this demo provides a good prototype, and its architecture and design ideas are worth learning from. It also provides detailed Chinese design documents. It is a rare reference.
3 name: Basic Chinese Information Processing
Address: http://ccl.pku.edu.cn/doubtfire/Course/Chinese%20Information%20Processing/2002_2003_1.htm
Evaluation: Peking University's Chinese Department of Linguistics graduate course, do not have to read Chinese word segmentation. It also provides good language materials.
Other scattered materials are of little significance. I can thoroughly study the above three documents. It is estimated that the developed word segmentation program is more accurate. So far, I haven't finished reading "Chinese Information Processing basics". To learn more, I guess I have to go to the "data structure self-testing Website" to lay the algorithm foundation well.
4 ktdictseg
Http://www.cnblogs.com/eaglet/tag/%e5%88%86%e8%af%8d/
5. http://www.cnblogs.com/kwklover/archive/2007/03/19/679327.html
Reprinted from: http://ruyu108.blog.163.com/blog/static/10123108200992262747545/