Current research in knowledge-based Word Sense Disambiguation (WSD) indicates that performances depend heavily on the Lexical Knowledge Base (LKB) employed. This paper introduces SyntagNet, a novel resource consisting of manually disambiguated lexical-semantic combinations. By capturing sense distinctions evoked by syntagmatic relations, SyntagNet enables knowledge-based WSD systems to establish a new state of the art which challenges the hitherto unrivaled performances attained by supervised approaches. To the best of our knowledge, SyntagNet is the first large-scale manually-curated resource of this kind made available to the community (at http://syntagnet.org)
SyntagNet: challenging supervised word sense disambiguation with Lexical-Semantic Combinations / Maru, Marco; Scozzafava, Federico; Martelli, Federico; Navigli, Roberto. - (2019), pp. 3532-3538. ((Intervento presentato al convegno Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) tenutosi a Hong Kong; China.
Titolo: | SyntagNet: challenging supervised word sense disambiguation with Lexical-Semantic Combinations |
Autori: | |
Data di pubblicazione: | 2019 |
Citazione: | SyntagNet: challenging supervised word sense disambiguation with Lexical-Semantic Combinations / Maru, Marco; Scozzafava, Federico; Martelli, Federico; Navigli, Roberto. - (2019), pp. 3532-3538. ((Intervento presentato al convegno Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) tenutosi a Hong Kong; China. |
Handle: | http://hdl.handle.net/11573/1344950 |
ISBN: | 978-1-950737-92-5 |
Appartiene alla tipologia: | 04b Atto di convegno in volume |
File allegati a questo prodotto
File | Note | Tipologia | Licenza | |
---|---|---|---|---|
Navigli_SyntagNet_2019.pdf | Versione editoriale (versione pubblicata con il layout dell'editore) | Tutti i diritti riservati (All rights reserved) | Open Access Visualizza/Apri |