IIT Home Page CNR Home Page

SemEval-2010 Task 17: All-wordsWord Sense Disambiguation on a Specific Domain

Domain portability and adaptation of NLP components and Word Sense Disambiguation  systems present new challenges. The diffi culties found by supervised systems to adapt  might change the way we assess the strengths  and weaknesses of supervised and knowledgebased WSD systems. Unfortunately, all existing evaluation datasets for specific domains  are lexical-sample corpora. With this paper  we want to motivate the creation of an allwords test dataset for WSD on the environment domain in several languages, and present  the overall design of this SemEval task.
NAACL HLT Workshop on Semantic Evaluations: Recent Achievements and Future Directions, Boulder, Colorado, 2009

Autori esterni: Eneko Agirre (EHU, ES), Oier Lopez de Lacalle (EHU, ES), Christiane Fellbaum (Princeton University, USA), Antonio Toral (ILC CNR, IT), Piek Vossen (Vrije Universiteit Amsterdam, Netherlands)
Autori IIT:

Tipo: Articolo in Atti di convegno internazionale
Area di disciplina: Information Technology and Communication Systems
Da pagina 123 a pagina 128

Attività: Social and Semantic Web
Web of Data