Unbalanced Optimal Transport for Unbalanced Word Alignment

Yuki Arase, Han Bao, Sho Yokoi


Abstract
Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.
Anthology ID:
2023.acl-long.219
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3966–3986
Language:
URL:
https://aclanthology.org/2023.acl-long.219
DOI:
10.18653/v1/2023.acl-long.219
Bibkey:
Cite (ACL):
Yuki Arase, Han Bao, and Sho Yokoi. 2023. Unbalanced Optimal Transport for Unbalanced Word Alignment. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3966–3986, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Unbalanced Optimal Transport for Unbalanced Word Alignment (Arase et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.219.pdf
Video:
 https://aclanthology.org/2023.acl-long.219.mp4