SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation

Ziyao Xu, Houfeng Wang


Abstract
Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and lacks consideration of large language models (LLMs), which cannot fully cover practical application scenarios. In this work, we propose SPOR, a comprehensive and practical evaluation method for compositional generalization in data-to-text generation. SPOR includes four aspects of manifestations (Systematicity, Productivity, Order invariance, and Rule learnability) and allows high-quality evaluation without additional manual annotations based on existing datasets. We demonstrate SPOR on two different datasets and evaluate some existing language models including LLMs. We find that the models are deficient in various aspects of the evaluation and need further improvement. Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.
Anthology ID:
2024.acl-long.36
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:
604–621
Language:
URL:
https://aclanthology.org/2024.acl-long.36
DOI:
Bibkey:
Cite (ACL):
Ziyao Xu and Houfeng Wang. 2024. SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 604–621, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation (Xu & Wang, ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.36.pdf