(CRF Chinese word segmentation open source version Chinese word segmentation is one of the basic technologies that are indispensable for Internet use, and it is also an indispensable technical component of other speech and language products. Since the first World Chinese Word Segmentation Evaluation in 2003, the word segmentation method based on word formation has achieved an overwhelming advantage. In China, the CRF open source software package is the first to learn the word segmentation method, but the code structure of CRF is too cluttered, resulting in this algorithm. penetration rate. The CRF Chinese word segmentation open source version only includes the word segmentation decoder part of the CRF software package, which simplifies the CRF messy code structure, clears the code that the word segmentation decoder does not need, and greatly improves the readability and intelligibility of the word segmentation decoder. At the same time, in order to facilitate the learners to visually track and debug the code, two project files, VC6.0 and VS2008, were built under the Windows platform, so that VC6.0 users and VS2008 users can easily play Chinese word segmentation. The word segmentation knowledge base in the open source package is small and the word segmentation accuracy is low. It is only used for learning the Crf word segmentation algorithm. You can obtain a higher precision word segmentation knowledge base and a higher speed word segmentation engine DLL or OCX through the following paths: 1) Call nlptech360 @gmail or langiner@gmail 2) Leave a message on the blog langiner.blog.51cto 3) Search on the search engine: extremely fast word segmentation
CrfDeocder-windows-source\common.h
CrfDeocder-windows-source\crf_test-vc6.0.dsp
CrfDeocder-windows-source\crf_test-vc6.0.dsw
CrfDeocder-windows-source\crf_test-vs2008.sln
CrfDeocder-windows-source\crf_test-vs2008.vcproj
CrfDeocder-windows-source\crf_test.cpp
CrfDeocder-windows-source\darts.h
CrfDeocder-windows-source\feature.cpp
CrfDeocder-windows-source\feature_cache.cpp
CrfDeocder-windows-source\feature_cache.h
CrfDeocder-windows-source\feature_index.cpp
CrfDeocder-windows-source\feature_index.h
CrfDeocder-windows-source\free.model
CrfDeocder-windows-source\freelist.h
CrfDeocder-windows-source\mmap.h
CrfDeocder-windows-source\node.h
CrfDeocder-windows-source\path.h
CrfDeocder-windows-source\readme.txt
CrfDeocder-windows-source\scoped_ptr.h
CrfDeocder-windows-source\tagger.cpp
CrfDeocder-windows-source\tagger.h
CrfDeocder-windows-source\test.txt)
收藏
