This paper describes SEW-EMBED, our language-independent approach to multilingual and cross-lingual semantic word similarity as part of the SemEval-2017 Task 2. We leverage the Wikipedia-based concept representations developed by Raganato et al. (2016), and propose an embedded augmentation of their explicit high-dimensional vectors, which we obtain by plugging in an arbitrary word (or sense) embedding representation, and computing a weighted average in the continuous vector space. We evaluate SEW-EMBED with two different off-the-shelf embedding representations, and report their performances across all monolingual and cross-lingual benchmarks available for the task. Despite its simplicity, especially compared with supervised or overly tuned approaches, SEW-EMBED achieves competitive results in the cross-lingual setting (3rd best result in the global ranking of subtask 2, score 0.56).

Delli Bovi, C., Raganato, A. (2017). SEW-EMBED at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp.261-266). Association for Computational Linguistics.

SEW-EMBED at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia

Raganato, Alessandro
2017

Abstract

This paper describes SEW-EMBED, our language-independent approach to multilingual and cross-lingual semantic word similarity as part of the SemEval-2017 Task 2. We leverage the Wikipedia-based concept representations developed by Raganato et al. (2016), and propose an embedded augmentation of their explicit high-dimensional vectors, which we obtain by plugging in an arbitrary word (or sense) embedding representation, and computing a weighted average in the continuous vector space. We evaluate SEW-EMBED with two different off-the-shelf embedding representations, and report their performances across all monolingual and cross-lingual benchmarks available for the task. Despite its simplicity, especially compared with supervised or overly tuned approaches, SEW-EMBED achieves competitive results in the cross-lingual setting (3rd best result in the global ranking of subtask 2, score 0.56).
paper
semantic similarity; multilinguality; concept vectors; embeddings; word sense disambiguation; wikipedia
English
11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - 3 August 2017 through 4 August 2017
2017
Proceedings of the Annual Meeting of the Association for Computational Linguistics
9781945626555
2017
1
261
266
reserved
Delli Bovi, C., Raganato, A. (2017). SEW-EMBED at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp.261-266). Association for Computational Linguistics.
File in questo prodotto:
File Dimensione Formato  
S17-2041.pdf

Solo gestori archivio

Dimensione 352.05 kB
Formato Adobe PDF
352.05 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/10281/361551
Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
Social impact