Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. Despite the recent introduction of Word Embeddings and Recurrent Neural Networks to design powerful context-related features, the interest in improving WSD models using Semantic Lexical Resources (SLRs) is mostly restricted to knowledge-based approaches. In this paper, we enhance “modern” supervised WSD models exploiting two popular SLRs: WordNet and WordNet Domains. We propose an effective way to introduce semantic features into the classifiers, and we consider using the SLR structure to augment the training data. We study the effect of different types of semantic features, investigating their interaction with local contexts encoded by means of mixtures of Word Embeddings or Recurrent Neural Networks, and we extend the proposed model into a novel multi-layer architecture for WSD. A detailed experimental comparison in the recent Unified Evaluation Framework (Raganato et al., 2017) shows that the proposed approach leads to supervised models that compare favourably with the state-of-the art.

Melacci, S., Achille, G., Rigutini, L. (2018). Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC) (pp.1012-1017). European Language Resources Association.

Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources

Stefano Melacci
;
Leonardo Rigutini
2018-01-01

Abstract

Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. Despite the recent introduction of Word Embeddings and Recurrent Neural Networks to design powerful context-related features, the interest in improving WSD models using Semantic Lexical Resources (SLRs) is mostly restricted to knowledge-based approaches. In this paper, we enhance “modern” supervised WSD models exploiting two popular SLRs: WordNet and WordNet Domains. We propose an effective way to introduce semantic features into the classifiers, and we consider using the SLR structure to augment the training data. We study the effect of different types of semantic features, investigating their interaction with local contexts encoded by means of mixtures of Word Embeddings or Recurrent Neural Networks, and we extend the proposed model into a novel multi-layer architecture for WSD. A detailed experimental comparison in the recent Unified Evaluation Framework (Raganato et al., 2017) shows that the proposed approach leads to supervised models that compare favourably with the state-of-the art.
2018
979-10-95546-00-9
Melacci, S., Achille, G., Rigutini, L. (2018). Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC) (pp.1012-1017). European Language Resources Association.
File in questo prodotto:
File Dimensione Formato  
melacci_LREC2018.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 288.38 kB
Formato Adobe PDF
288.38 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11365/1065977