Abstract
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts. While there have been approaches for NLP tasks that require comparative reasoning, they suffer from costly manual data labeling and limited generalizability to different tasks. Our approach introduces a novel method of collecting scalable data for text-based entity comparison, which leverages both structured and unstructured data. Moreover, we present a framework of pre-training language models via three novel objectives on comparative reasoning. Evaluation on downstream tasks including comparative question answering, question generation, and summarization shows that our pre-training framework significantly improves the comparative reasoning abilities of language models, especially under low-resource conditions. This work also releases the first integrated benchmark for comparative reasoning.- Anthology ID:
- 2023.emnlp-main.763
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12421–12433
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.763
- DOI:
- 10.18653/v1/2023.emnlp-main.763
- Cite (ACL):
- Mengxia Yu, Zhihan Zhang, Wenhao Yu, and Meng Jiang. 2023. Pre-training Language Models for Comparative Reasoning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12421–12433, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Pre-training Language Models for Comparative Reasoning (Yu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.emnlp-main.763.pdf