A Relaxed Matching Procedure for Unsupervised BLI

Xu Zhao, Zihao Wang, Yong Zhang, Hao Wu


Abstract
Recently unsupervised Bilingual Lexicon Induction(BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.
Anthology ID:
2020.acl-main.274
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3036–3041
Language:
URL:
https://aclanthology.org/2020.acl-main.274
DOI:
10.18653/v1/2020.acl-main.274
Bibkey:
Cite (ACL):
Xu Zhao, Zihao Wang, Yong Zhang, and Hao Wu. 2020. A Relaxed Matching Procedure for Unsupervised BLI. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3036–3041, Online. Association for Computational Linguistics.
Cite (Informal):
A Relaxed Matching Procedure for Unsupervised BLI (Zhao et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.274.pdf
Video:
 http://slideslive.com/38929428