Improving Compositional Generalization in Classification Tasks via Structure Annotations

Juyong Kim, Pradeep Ravikumar, Joshua Ainslie, Santiago Ontanon


Abstract
Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models struggle to do so. In this work, we study compositional generalization in classification tasks and present two main contributions. First, we study ways to convert a natural language sequence-to-sequence dataset to a classification dataset that also requires compositional generalization. Second, we show that providing structural hints (specifically, providing parse trees and entity links as attention masks for a Transformer model) helps compositional generalization.
Anthology ID:
2021.acl-short.81
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
637–645
Language:
URL:
https://aclanthology.org/2021.acl-short.81
DOI:
10.18653/v1/2021.acl-short.81
Bibkey:
Cite (ACL):
Juyong Kim, Pradeep Ravikumar, Joshua Ainslie, and Santiago Ontanon. 2021. Improving Compositional Generalization in Classification Tasks via Structure Annotations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 637–645, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Compositional Generalization in Classification Tasks via Structure Annotations (Kim et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.81.pdf
Video:
 https://aclanthology.org/2021.acl-short.81.mp4
Data
CFQ