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/