Resources
Home ] Syllabus ] Assignments and Project ] Schedule ] Calendar ] [ Resources ]

 

 

Weizenbaum, J., "ELIZA -- A computer program for the study of natural language communication between man and machine", Communications of the ACM 9(1):36-45, 1966.

    Eliza demo: http://www.manifestation.com/neurotoys/eliza.php3

Extractor is software for automatically summarizing text, developed by the Interactive Information Group, National Research Council. Extractor takes a text file as input and generates a list of key words and a list of key sentences as output. Here is a paper about Extractor by Peter Turney.

Concordance demo by Cobuild 

NLP dictionary by Bill Wilson

Information Extraction Tutorial by Doug Appelt and David Israel

The CMU-Cambridge Statistical Language Modeling Toolkit is a suite of UNIX software tools to facilitate the construction and testing of statistical language models.

Project Gutenberg is the Internet's oldest producer of free electronic texts.

The Reuters-21578 Text Categorization Test Collection

Resources of Text Categorization

The NLP Toolkit is a Python package intended to simplify the task of programming natural language systems.

World Wide Web Virtual Library: Linguistics

Association for Computational Linguistics - student membership is just $30/year and includes the journal

Computational Linguistics - the main CL journal

The ACL NLP/CL Universe - pointers to conferences, schools, jobs, resources, ...

Computing Research Repository - access to online papers on Computational Linguistics

Statistical NLP and corpus-based CL - an annotated list of resources

CMU-Cambridge Toolkit - a suite of Unix tools to facilitate the construction and testing of statistical language models

NLP FAQ - answers to frequently asked questions about NLP

Handbook of the International Phonetic Association - includes online audio files

SIL Glossary of Linguistic Terms

Survey of the State of the Art in Human Language Technology

Corpus Linguistics - Michael Barlow's page of links

Newsgroups: sci.lang, comp.ai.nat-lang

The Berkeley FrameNet project is creating an online lexical resource for English, based on frame semantics and supported by corpus evidence.

WordNet® is an online lexical reference system whose design is inspired by current psycholinguistic theories of human lexical memory

Parsers

Michael Collins parser

Eugene Charniak's parser.

Dekang Lin's parser

 

 

Home ]

Copyright © 2004 Dekang Lin
Last modified: June 09, 2003