We present a multilingual joint approach to Word Sense Disambiguation (WSD). Our method exploits BabelNet, a very large multilingual knowledge base, to perform graph-based WSD across different languages, and brings together empirical evidence from these languages using ensemble methods. The results show that, thanks to complementing wide-coverage multilingual lexical knowledge with robust graph-based algorithms and combination methods, we are able to achieve the state of the art in both monolingual and multilingual WSD settings.
Joining Languages Pays Off: A Multilingual Joint Approach to Knowledge-based Word Sense Disambiguation / Navigli, Roberto; Ponzetto, SIMONE PAOLO. - STAMPA. - (2012). (Intervento presentato al convegno 2012 Conference on Empirical Methods in Natural Language Processing tenutosi a Jeju, Korea nel July 12-14, 2012).
Joining Languages Pays Off: A Multilingual Joint Approach to Knowledge-based Word Sense Disambiguation
NAVIGLI, ROBERTO;PONZETTO, SIMONE PAOLO
2012
Abstract
We present a multilingual joint approach to Word Sense Disambiguation (WSD). Our method exploits BabelNet, a very large multilingual knowledge base, to perform graph-based WSD across different languages, and brings together empirical evidence from these languages using ensemble methods. The results show that, thanks to complementing wide-coverage multilingual lexical knowledge with robust graph-based algorithms and combination methods, we are able to achieve the state of the art in both monolingual and multilingual WSD settings.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
