Recent years have seen a dramatic growth in the popularity of word embeddings mainly owing to their ability to capture semantic information from massive amounts of textual content. As a result, many tasks in Natural Language Processing have tried to take advantage of the potential of these distributional models. In this work, we study how word embeddings can be used in Word Sense Disambiguation, one of the oldest tasks in Natural Language Processing and Artificial Intelligence. We propose different methods through which word embeddings can be leveraged in a state-of-the-art supervised WSD system architecture, and perform a deep analysis of how different parameters affect performance. We show how a WSD system that makes use of word embeddings alone, if designed properly, can provide significant performance improvement over a state-of-the-art WSD system that incorporates several standard WSD features.

Embeddings for word sense disambiguation: an evaluation study / Iacobacci, IGNACIO JAVIER; Pilehvar, MOHAMMED TAHER; Navigli, Roberto. - ELETTRONICO. - 2:(2016), pp. 897-907. (Intervento presentato al convegno 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 tenutosi a Berlin nel 2016).

Embeddings for word sense disambiguation: an evaluation study

IACOBACCI, IGNACIO JAVIER;PILEHVAR, MOHAMMED TAHER;NAVIGLI, Roberto
2016

Abstract

Recent years have seen a dramatic growth in the popularity of word embeddings mainly owing to their ability to capture semantic information from massive amounts of textual content. As a result, many tasks in Natural Language Processing have tried to take advantage of the potential of these distributional models. In this work, we study how word embeddings can be used in Word Sense Disambiguation, one of the oldest tasks in Natural Language Processing and Artificial Intelligence. We propose different methods through which word embeddings can be leveraged in a state-of-the-art supervised WSD system architecture, and perform a deep analysis of how different parameters affect performance. We show how a WSD system that makes use of word embeddings alone, if designed properly, can provide significant performance improvement over a state-of-the-art WSD system that incorporates several standard WSD features.
2016
54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Language and Linguistics; Natural language processing systems
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Embeddings for word sense disambiguation: an evaluation study / Iacobacci, IGNACIO JAVIER; Pilehvar, MOHAMMED TAHER; Navigli, Roberto. - ELETTRONICO. - 2:(2016), pp. 897-907. (Intervento presentato al convegno 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 tenutosi a Berlin nel 2016).
File allegati a questo prodotto
File Dimensione Formato  
Iacobacci_Embedding_2016.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 264.41 kB
Formato Adobe PDF
264.41 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/936571
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 205
  • ???jsp.display-item.citation.isi??? 122
social impact