NLP常用工具

NLP常用工具

各种工具包的有效利用可以使研究者事半功倍。 
以下是NLP版版友们提供整理的NLP研究工具包。 
同时欢迎大家提供更多更好用的工具包，造福国内的NLP研究。 

*NLP Toolbox 
  CLT   http://complingone.georgetown.edu/~linguist/compling.html 
  GATE   http://gate.ac.uk/ 
  Natural Language Toolkit(NLTK)   http://nltk.org 
  MALLET   http://mallet.cs.umass.edu/index.php/Main_Page 
  OpenNLP   http://opennlp.sourceforge.net/ 

*English Stemmer 
  Snowball   http://snowball.tartarus.org/ 

*English POS Tagger 
  Stanford POS Tagger   http://nlp.stanford.edu/software/tagger.shtml 
  TreeTagger   http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/ 
  TnT   http://www.coli.uni-saarland.de/~thorsten/tnt/ 

*English&Chinese Parser 
  Stanford Parser   http://nlp.stanford.edu/software/lex-parser.shtml 
  Berkeley Parser   http://nlp.cs.berkeley.edu/Main.html#Parsing 

*English Keyphrase Extractor 
  KEA   http://www.nzdl.org/Kea/index_old.html 
   
*English Name Entity Recognizer 
  Stanford NER   http://nlp.stanford.edu/software/CRF-NER.shtml 

*Chinese Word Segmentator 
  中科院ICTCLAS   http://www.nlp.org.cn/project/project.php?proj_id=6 
  Stanford Word Segmenter   http://nlp.stanford.edu/software/segmenter.shtml 

*Topic Modeling Tools 
  Matlab   http://psiexp.ss.uci.edu/research/programs_data/toolbox.htm 
  GibbsLDA++   http://gibbslda.sourceforge.net/ 
  GLDA   http://code.google.com/p/glda/ 

*Conditional Random Fields 
  FlexCRFs   http://flexcrfs.sourceforge.net/ 含有MPI并行版本。 
  CRF++    http://crfpp.sourFceforge.net/ 
  CRF Package   http://crf.sourceforge.net/ 
  CRF Matlab   http://www.cs.ubc.ca/~murphyk/Software/CRFall.zip 
  CRFSuit   http://www.chokkan.org/software/crfsuite/ 
  SGD with CRF   http://leon.bottou.org/projects/sgd 
  HCRF   http://sourceforge.net/projects/hcrf/ 

*Support Vector Machine  
  LIBSVM   http://www.csie.ntu.edu.tw/~cjlin/libsvm/ 
  LIBLINEAR   http://www.csie.ntu.edu.tw/~cjlin/liblinear/ 
  Pegasos   http://www.cs.huji.ac.il/~shais/code/index.html 

*Search Engines 
  Lucene   http://lucene.apache.org/ 
  中科院FirteX   http://www.firtex.org/ 

*Machine Learning and Data Mining Toolbox 
  Weka   http://www.cs.waikato.ac.nz/ml/weka/