See also:

• Reference: Knowledge Management: Knowledge Discovery: Text Mining  (26)

AFGL Project: Affix Grammars over a Finite Lattice - - A system of public domain software for natural language processing. Includes a formalism for compact grammar description, parser generation system, transduction tool.

Annotate - - Tool for semi-automatic graphic annotation of corpora. License, documentation, screenshot. Requires GCC and MySQL, in addition to registration.

ARIES Natural Language Tools - - Proprietary tools for the lexical work on the Spanish language. Free demo, documentation.

Cogilex - - Company offering expert services and customized tools for natural language processing. Site features demo download of the "QuickTag and QuickParse" utility for Windows, also online tools.

Connexor Parsers - - Language parsers and taggers for English, German, French, Spanish, Italian, Dutch, Finnish and Swedish. On-line parser demos and limited documentation available.

GATE: General Architecture for Text Engineering - - A computer architecture for a broad range of Natural Language Processing tasks, available under the GNU Public License. Abundant documentation, Java class library, web-based demos.

GroupLens - - An experimental collaborative filtering service based on "Better Bit Bureaus" which is itself a collaborative venture between Paul Resnik of the Center for Coordination Science at MIT and Brad Miller and others at the University of Minnesot.

KPML Access Page - - Graphically based language engineering program, developed for working with large-scale grammars under the Systemic Formal Linguistics framework. Downloadable program images, documentation, resources and source code.

Morphological and Orthographic Tools for English - - UNIX tools for the analysis and synthesis of text, from Sussex's John Carroll. GZIP downloads, descriptions, related publications.

Natural Language Software Registry - - A directory of academic, commercial and proprietary software with specifications and licensing terms. From DFKI Saarbrücken.

OpenNLP - - Collaborative organization for open source projects related to natural language processing. Lists ongoing projects and documents proposed standard Java and XML APIs.

Phrasys Natural Language Processing - - A variety of services for natural language technology developers, including consultancy, commercial software and freeware. Features a Java component useful for string analysis.

Public Domain Language Engineering Generic Tools - - Lecture by Tomaz Erjavec, including text, slides and links. From the 1996 TELRI conference.

Senga: Information Retrieval Software - - Senga is a development group focused on information retrieval software. The primary purpose of the components distributed on Senga is to build a large scale internet search engine.

Smart Tutorial - - A tutorial on the SMART IR system from Cornell. Put together by Hans Paijmans with a technical report on the implementation of an earlier version of SMART.

TextAI: Text Analysis International - - Provides NLP applications based on its proprietary VisualText technology. Product and service information, online software tour, some documentation.

Thistle - - A Java GUI editor for editing tree diagrams (such as those employed in constraint-based grammars), existing in both applet and standalone forms. Sample trees and editors.