IIT Home Page CNR Home Page

SemEval-2010 task 17: All-words word sense disambiguation on a specific domain

Domain portability and adaptation of NLP components and Word Sense Disambiguation systems present new challenges. The difficulties found by supervised systems to adapt might change the way we assess the strengths and weaknesses of supervised and knowledge-based WSD systems. Unfortunately, all existing evaluation datasets for specific domains are lexical-sample corpora. This task presented all-words datasets on the environment domain for WSD in four languages (Chinese, Dutch, English, Italian). 11 teams participated, with supervised and knowledge-based systems, mainly in the English dataset. The results show that in all languages the participants where able to beat the most frequent sense heuristic as estimated from general corpora. The most successful approaches used some sort of supervision in the form of hand-tagged examples from the domain.
SemEval '10, Uppsala, Svezia, 2010

Autori esterni: Eneko Agirre (IXA NLP group, UBC, Donostia, Basque Country), Oier Lopez de Lacalle (IXA NLP group, UBC, Donostia, Basque Country), Christiane Fellbaum (Princeton University, Princeton), Shu-Kai Hsieh National (Taiwan Normal University, Taipei, Taiwan), Monica Monachini (ILC, CNR, Pisa, Italy), Piek Vossen (Vrije Universiteit Amsterdam, Amsterdam, Netherlands), Roxanne Segers (Vrije Universiteit Amsterdam, Amsterdam, Netherlands)
Autori IIT:

Tipo: Articolo in Atti di convegno internazionale con referee
Area di disciplina: Computer Science & Engineering
Da pagina 75 a pagina 80

Attività: Multilingual Web