Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao


Abstract
Compositional generalization, representing the model’s ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods. Nonetheless, a comprehensive compositional generalization evaluation benchmark of MCTG is still lacking. We propose CompMCTG, a benchmark encompassing diverse multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol, to holistically evaluate the compositional generalization of MCTG approaches. We observe that existing MCTG works generally confront a noticeable performance drop in compositional testing. To mitigate this issue, we introduce Meta-MCTG, a training framework incorporating meta-learning, where we enable models to learn how to generalize by simulating compositional generalization scenarios in the training phase. We demonstrate the effectiveness of Meta-MCTG through achieving obvious improvement (by at most 3.64%) for compositional testing performance in 94.4%.
Anthology ID:
2024.acl-long.351
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6486–6517
Language:
URL:
https://aclanthology.org/2024.acl-long.351
DOI:
10.18653/v1/2024.acl-long.351
Bibkey:
Cite (ACL):
Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, and Zhendong Mao. 2024. Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6486–6517, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (Zhong et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.351.pdf