Equivariant Transduction through Invariant Alignment

Jennifer C. White, Ryan Cotterell


Abstract
The ability to generalize compositionally is key to understanding the potentially infinite number of sentences that can be constructed in a human language from only a finite number of words. Investigating whether NLP models possess this ability has been a topic of interest: SCAN (Lake and Baroni, 2018) is one task specifically proposed to test for this property. Previous work has achieved impressive empirical results using a group-equivariant neural network that naturally encodes a useful inductive bias for SCAN (Gordon et al., 2020). Inspired by this, we introduce a novel group-equivariant architecture that incorporates a group-invariant hard alignment mechanism. We find that our network’s structure allows it to develop stronger equivariance properties than existing group-equivariant approaches. We additionally find that it outperforms previous group-equivariant networks empirically on the SCAN task. Our results suggest that integrating group-equivariance into a variety of neural architectures is a potentially fruitful avenue of research, and demonstrate the value of careful analysis of the theoretical properties of such architectures.
Anthology ID:
2022.coling-1.412
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4651–4663
Language:
URL:
https://aclanthology.org/2022.coling-1.412
DOI:
Bibkey:
Cite (ACL):
Jennifer C. White and Ryan Cotterell. 2022. Equivariant Transduction through Invariant Alignment. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4651–4663, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Equivariant Transduction through Invariant Alignment (White & Cotterell, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.412.pdf
Code
 rycolab/equivariant-transduction