A Rank-Based Similarity Metric for Word Embeddings

Enrico Santus, Hongmin Wang, Emmanuele Chersoni, Yue Zhang


Abstract
Word Embeddings have recently imposed themselves as a standard for representing word meaning in NLP. Semantic similarity between word pairs has become the most common evaluation benchmark for these representations, with vector cosine being typically used as the only similarity metric. In this paper, we report experiments with a rank-based metric for WE, which performs comparably to vector cosine in similarity estimation and outperforms it in the recently-introduced and challenging task of outlier detection, thus suggesting that rank-based measures can improve clustering quality.
Anthology ID:
P18-2088
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
552–557
Language:
URL:
https://aclanthology.org/P18-2088
DOI:
10.18653/v1/P18-2088
Bibkey:
Cite (ACL):
Enrico Santus, Hongmin Wang, Emmanuele Chersoni, and Yue Zhang. 2018. A Rank-Based Similarity Metric for Word Embeddings. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 552–557, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
A Rank-Based Similarity Metric for Word Embeddings (Santus et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2088.pdf
Software:
 P18-2088.Software.zip
Poster:
 P18-2088.Poster.pdf