A language-independent LESK based approach to Word Sense Disambiguation

Tommaso Petrolito


Abstract
This paper describes a language- independent LESK based approach to Word Sense Disambiguation (WSD), involving also Vector Space Models applied to the Distributional Semantics Hypotesis. In particular this approach tries to solve some issues that come up with less-resourced languages. The approach also addresses the inadequacy of the Most Frequent Sense (MFS) heuristics to fit specific domain corpora.
Anthology ID:
2016.gwc-1.40
Volume:
Proceedings of the 8th Global WordNet Conference (GWC)
Month:
27--30 January
Year:
2016
Address:
Bucharest, Romania
Editors:
Christiane Fellbaum, Piek Vossen, Verginica Barbu Mititelu, Corina Forascu
Venue:
GWC
SIG:
SIGLEX
Publisher:
Global Wordnet Association
Note:
Pages:
275–281
Language:
URL:
https://aclanthology.org/2016.gwc-1.40
DOI:
Bibkey:
Cite (ACL):
Tommaso Petrolito. 2016. A language-independent LESK based approach to Word Sense Disambiguation. In Proceedings of the 8th Global WordNet Conference (GWC), pages 275–281, Bucharest, Romania. Global Wordnet Association.
Cite (Informal):
A language-independent LESK based approach to Word Sense Disambiguation (Petrolito, GWC 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2016.gwc-1.40.pdf