Nothing Special   »   [go: up one dir, main page]

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base

Siyu Yuan, Jiangjie Chen, Changzhi Sun, Jiaqing Liang, Yanghua Xiao, Deqing Yang


Abstract
Analogical reasoning is a fundamental cognitive ability of humans. However, current language models (LMs) still struggle to achieve human-like performance in analogical reasoning tasks due to a lack of resources for model training. In this work, we address this gap by proposing ANALOGYKB, a million-scale analogy knowledge base (KB) derived from existing knowledge graphs (KGs). ANALOGYKB identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large language models (LLMs), followed by minor human efforts for data quality control. Evaluations on a series of datasets of two analogical reasoning tasks (analogy recognition and generation) demonstrate that ANALOGYKB successfully enables both smaller LMs and LLMs to gain better analogical reasoning capabilities. Resources of this paper can be found at https://github.com/siyuyuan/analogykb.
Anthology ID:
2024.acl-long.68
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:
1249–1265
Language:
URL:
https://aclanthology.org/2024.acl-long.68
DOI:
10.18653/v1/2024.acl-long.68
Bibkey:
Cite (ACL):
Siyu Yuan, Jiangjie Chen, Changzhi Sun, Jiaqing Liang, Yanghua Xiao, and Deqing Yang. 2024. ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1249–1265, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base (Yuan et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.68.pdf