Joining forces pays off: multilingual joint word sense disambiguation

  • Authors:
  • Roberto Navigli;Simone Paolo Ponzetto

  • Affiliations:
  • Sapienza Università di Roma;Sapienza Università di Roma

  • Venue:
  • EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

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.