INTRODUCTION

GLOSSARY

CORPORA

COURSES

BIBLIOGRAPHY

RELATED SITES

SOFTWARE

SEARCH ENGINE

TUTORIAL

COMMENTS

CONTENT

• General sites
• Concordancing
• Tagging & Parsing
• Misc.

• LEXA: Corpus Processing Software
• The Linguist List : site with info on software
  maintained and updated by the Linguist List.
• MULTEX. Multilingual Text Tools and Corpora.
  Series of tools for accessing and manipulating corpora (under development).
• Summer Institute of Linguistics (SIL) list of software.
• Christopher Manning's annotated list of resources on statistical NLP and corpus-based computational linguistics.
• Michael Barlow's Corpus Linguistics pages (software).
• Tomaz Erjavec paper giving "overview of language engineering public domain and freely available software".

Concordancing tools

• Conc
  a Mac concordance program.
• MonoConc
  a Mac/Windows concordance program that allows sorts (2R,1R,2L,1L) and provides simple frequency information.
• OCP: The Oxford Concordance Program.
• ParaConc
  a Mac/Windows concordance program for parallel texts. A version is available for free for research purposes (under license).
• SARA (SGML-Aware Retrieval Application)
  MS-Windows-based concordance and word-frequency package. Especially set up for BNC.
• TACT (Text Analysis Computing Tools)
  MS-DOS programs "designed to do text-retrieval and analysis on literary works".
• WordSmith Tools
  Easy-to-use MS-Windows programs for generating word frequency listings and concordances.
• MicroConcord
  produced by Oxford University Press. (Demo via ftp.)
• XKwic
  Fast Concordance Program for X-Windows. University of Stuttgart project "Textual Corpora and Tools for their exploration".

Tagging & Parsing (available software or on-line tagging)

• Amalgam Tagger (Univ. of Leeds)
  Enter text via e-mail and have it tagged. Choice of eight tagging schemes.
• The AMAZON parser AutoMAtische ZinsONtleding (automatic analysis of sentences). Dutch only.
• Apple Pie Parser
  "bottom-up probabilistic chart parser which finds the parse tree with the best score by best-first search algorithm." (Available by ftp)
• Brill:Trainable Part of Speech Tagger
  Rule-based part of speech tagger (available by ftp).
• Conexor linguistic software developed in Finland.
  "based on linguistic generalisations and rules rather than linguistically naive corpus probabilities"
• Dependency Parser of English.
  Parse English text on-line (WWW demo).
• EngCG Parser
  Constraint Grammar Parser of English. (Use online)
• EngCG tagger
  Constraint Grammar tagging of English.
  
• EngCG-2 tagger
  Newer version of EngCG tagger (Constraint Grammar tagging of English). WWW demo
• EngLite parser
  "a fast, light parser that assigns word class and shallow syntactic tags to words in English texts" (Conexor) WWW demo
• Ergo Linguistic Technology Parser
  Online demo.
• FDG Functional Dependency Grammar of English
  "builds functionally labelled dependency links between words and assigns morphosyntactic tags to words"(Conexor) WWW demo
• Georgetown University Natural Language Processing Parser Modularity Demo
• Link Grammar Parser
  Syntactic parsing of English. Use on-line or download (MS Windows or Unix).
• MBT Memory Based Tagging.
  Demo. Tags text in Dutch, English, or Spanish online.
• TOSCA/LOB tagger for English.
  Available (MS-DOS) by ftp.
• QTAG Part of speech tagger
  Java/C from Birmingham U. (Oliver Mason).
• XRCE Part of Speech Disambiguators (Xerox Research Centre)
  Tag text online in French, Dutch, English, German, Spanish, Portuguese, Italian.