Re: Research on Tokenisation

Markku Norberg (norberg@lingsoft.fi)
Wed, 21 Aug 1996 19:31:32 +0300

Lingsoft, Inc.
-------------

http://www.lingsoft.fi/

This Helsinki, Finland software company which develops linguistics
software for text retrieval and information management systems,
specializes in the processing of English, German, Swedish,
Finnish. Also Estonian, Russian, Swahili. Coming: French, Italian,
Norwegian.

Examples:

Morphological analysis:

ENGTWOL (English)
Contains 75,000 base forms, recognizing over 300,000 word forms. See
the ENGTWOL demo (http://www.lingsoft.fi/cgi-pub/engtwol)!

Syntax:

ENGCG (English Constraint Grammar)
A general surface syntactic constraint grammar with a full functional
tag set for English (correctness 99.7%, ambiguity left 3-7%). See the
ENGCG demo (http://www.lingsoft.fi/cgi-pub/engcg)!

Our products are available for academic and non-profit
research. Please contact:

Markku Norberg
Markku.Norberg@lingsoft.fi

Lingsoft, Inc.
Museokatu 18 A
00100 Helsinki
Finland
tel. +350 9 499 556
fax +358 9 440 602