Abstract
Lexieal disambiguation can be achieved using different sources of information. Aiming at high performance of automatic disambiguation it is important to know the relative importance and applicability of the various sources. In this paper we classify several sources of information and show how some of them can be achieved using statistical data. First evaluations indicate the extreme importance of local information, which mainly represents lexical associations and seleetional restrictions for syntactically related words.
| Original language | English |
|---|---|
| Pages (from-to) | 341-342 |
| Number of pages | 2 |
| Journal | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
| Volume | 1991-June |
| State | Published - 1991 |
| Externally published | Yes |
| Event | 29th Annual Meeting of the Association for Computational Linguistics, ACL 1991 - Berkeley, United States Duration: 18 Jun 1991 → 21 Jun 1991 |
Bibliographical note
Publisher Copyright:© 1991 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All rights reserved.