This web page contains a number of software and data resources that I have used over the years.

Software


Parsers

Collin's Parser
Charniak's Parser
MINIPAR (dependency parser)

POS Taggers

TnT
MXPOST
LT POS
Brill's POS tagger

MT

Giza++
EGYPT
IBM Model 4 decoder
Pharaoh (phrase based decoder)

MT Evaluation

NIST Evaluation Toolkit (BLEU and NIST)
NYU Evaluation Toolkit

Language Modeling

SRI Language Model
CMU

Classification

Rainbow
Weka
BoostTexter
SVM-light
Bayes Net Toolbox
Matlab classification

Data


LDC
Europarl
UCI Repository

Thesuari

WordNet (including various interfaces)
Dekang Lin's
Infomap (LSA)

Text Classification

Industry Sector
20 Newsgroups
Reuters-21587

Misc. Links


Stanford Stat NLP Resources
AMTA