Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features.

Raganato, A., Delli Bovi, C., Navigli, R. (2017). Neural sequence learning models for word sense disambiguation. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp.1156-1167). Association for Computational Linguistics (ACL) [10.18653/v1/d17-1120].

Neural sequence learning models for word sense disambiguation

Raganato, Alessandro
;
2017

Abstract

Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features.
No
paper
Word Sense Disambiguation; Sequence Modeling; Neural Networks; Deep Learning;
English
2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - 7-11 Settembre
978-1-945626-83-8
https://aclweb.org/anthology/D/D17/D17-1121.pdf
Raganato, A., Delli Bovi, C., Navigli, R. (2017). Neural sequence learning models for word sense disambiguation. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp.1156-1167). Association for Computational Linguistics (ACL) [10.18653/v1/d17-1120].
Raganato, A; Delli Bovi, C; Navigli, R
File in questo prodotto:
File Dimensione Formato  
Navigli_Neural_2017.pdf

Solo gestori archivio

Dimensione 887.41 kB
Formato Adobe PDF
887.41 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/10281/361559
Citazioni
  • Scopus 132
  • ???jsp.display-item.citation.isi??? ND
Social impact