2017 SewEmbedatSemEval2017Task2Langu

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Sew-Embed; Multilingual And Cross-Lingual Semantic Word Similarity System; SemEval-2017 Task 2; Sew Corpus.

Notes

Cited By

Quotes

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).

References

BibTeX

@inproceedings{2017_SewEmbedatSemEval2017Task2Langu,
  author    = {Claudio Delli Bovi and
               Alessandro Raganato},
  editor    = {Steven Bethard and
               Marine Carpuat and
               Marianna Apidianaki and
               Saif M. Mohammad and
               Daniel M. Cer and
               David Jurgens},
  title     = {Sew-Embed at SemEval-2017 Task 2: Language-Independent Concept Representations
               from a Semantically Enriched Wikipedia},
  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval@ACL 2017)},
  pages     = {261--266},
  publisher = {Association for Computational Linguistics},
  year      = {2017},
  url       = {https://doi.org/10.18653/v1/S17-2041},
  doi       = {10.18653/v1/S17-2041},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2017 SewEmbedatSemEval2017Task2LanguAlessandro Raganato
Claudio Delli Bovi
Sew-Embed at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia2017