Developer of categorization, summarization, and metadata creation tools based on CIRCA technology, an ontology-based approach which organizes knowledge from unstructured content.

Software development kits providing language identification, word breaking, part-of-speech tagging, converting text to and from Unicode, entity extraction, name matching, and name translation.

Developers of software for individual PC users to collect and analyze data from the Internet. Features product overview, information on the company and contact details.

Develops software and custom content solutions for harvesting, classifying, and searching deep Web content.

Software that organizes large document sets into clusters of related documents, providing an overview of the document set and automating categorization with value for eDiscovery, from firm founded by Cornell physicist Bill Dimm.

Developer of search, auto-classification, taxonomy management software that uses concept extraction and "compound term processing" to generate semantic metadata from unstructured content.

McLean, Virginia firm supplying iDocXpt document management and information retrieval software to the US government and Defense Department.

A library of functions to implement the "N-Gram-Based Text Categorization" described by Cavnar and Trenkle, primarily developed for language guessing. News, download and documentation.

Shareware for textual pattern classification of Web sites to generate catalogs, electronic libraries, and other reference systems. Offers a demonstration version, help, and contact information for the author.