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
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 637–645
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-short.81/
- DOI:
- 10.18653/v1/2021.acl-short.81
- 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)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-short.81.pdf
- Data
- CFQ