CTI Textual Studies

Guide to Digital Resources 1996-98

Table of Contents


Description: CLAWS is part-of-speech tagging software developed by the University Centre for Computer Corpus Research on Language, at Lancaster University. The software works in three stages to assign a part-of-speech tag to each word or word combination in a text. CLAWS does this by drawing upon a lexicon of words and their possible parts of speech. The databases are constantly updated as new texts are processed. CLAWS also uses heuristics to process words which are not in the database. . The success rate for tagging is about 96-97% on average; manual post-editing will allow alterations and corrections to be made to the tags. CLAWS will also work on spoken text, though is less successful.

Requirements: PC.

Further information: See http://www.comp.lancs.ac.uk/computing/research/ucrel/annotation.html Also, Encoding the British National Corpus, Burnage and Dunlop (1994) at http://www.comp.lancs.ac.uk/computing/research/ucrel/papers/bncx27.html

Distributor: UCREL, Lancaster University, Bowland College, Lancaster, LA1 4YT. Tel: +44 1524 65201 ext. 3034 Fax: +44 1524 843085. Email: ucrel@lancaster.ac.uk

Price: Free

Version available at CTI Centre: None.

Search for:

Case sensitive    Partial match

[Resources Guide: A-Z Contents] [Resources Guide: Front Page] [CTI Textual Studies Home Page]

Guide to Digital Resources 1996-98. Not to be republished in any form without the permission of CTI Textual Studies.

HTML Author: Sarah Porter
Document Created: 16 June 1997
Document Modified:

The URL of this document is http://info.ox.ac.uk/ctitext/resguide/resources/c175.html