Journal of Siberian Federal University. Humanities & Social Sciences / Natural Language and Computational Linguistics at the University of Sussex

Full text (.pdf)
Issue
Journal of Siberian Federal University. Humanities & Social Sciences. 2008 1 (1)
Authors
Carroll, John A.
Contact information
Department of Informatics, University of Sussex Falmer Brighton BN1 9QJ, UK, e-mail:
Keywords
computer processing of human language, natural language processing, COGENT, DELPH-IN, RASP, SPARKLE, LEXSYS
Abstract

In this project we develop new ways of estimating the frequency distributions of the senses of words from raw (unannotated) text. We are starting to exploit these distributions to implement WSD systems which do not rely on the availability of hand-labelled resources. One way is to adopt the meaning distinctions set out in a particular dictionary or thesaurus and then to relate these distinctions to measures of similarity that we compute automatically between the occurrences of words in a text. Another way in which we use measures of word similarity is to automatically augment existing specialised thesauruses with new terms.

Pages
15-21
Paper at repository of SibFU
https://elib.sfu-kras.ru/handle/2311/651

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).