Contributo in atti di convegno, 2010, ENG

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

Agirre E.; López De Lacalle O.; Fellbaum C.; Hsieh S.; Tesconi M.; Monachini M.; Vossen P.; Vossen P.; Segers R.

University of the Basque Country, Spain, Princeton University, National Taiwan Normal Univ., CNR-IIT, Pisa, CNR-ILC, Pisa, Vrije Universiteit, Amsterdam

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.

ACL 2010- SemEval 2010: 5th International Workshop on Semantic Evaluation, pp. 75–80, Uppsala, Sweden, 15-16 Luglio 2010

Keywords

I.2.7 Natural Language Processing, Word Sense Disambiguation systems, Semantic Annotation, Word-sense disambiguation

CNR authors

Monachini Monica, Tesconi Maurizio

CNR institutes

IIT – Istituto di informatica e telematica, ILC – Istituto di linguistica computazionale "Antonio Zampolli"