A Two-Agent Game for Zero-shot Relation Triplet Extraction

Ting Xu, Haiqin Yang, Fei Zhao, Zhen Wu, Xinyu Dai

Abstract
Relation triplet extraction is a fundamental task in natural language processing that aims to identify semantic relationships between entities in text. It is particularly challenging in the zero-shot setting, i.e., zero-shot relation triplet extraction (ZeroRTE), where the relation sets between training and test are disjoint. Existing methods deal with this task by integrating relations into prompts, which may lack sufficient understanding of the unseen relations. To address these limitations, this paper presents a novel Two-Agent Game (TAG) approach to deliberate and debate the semantics of unseen relations. TAG consists of two agents, a generator and an extractor. They iteratively interact in three key steps: attempting, criticizing, and rectifying. This enables the agents to fully debate and understand the unseen relations. Experimental results demonstrate consistent improvement over ALBERT-Large, BART, andGPT3.5, without incurring additional inference costs in all cases. Remarkably, our method outperforms strong baselines by a significant margin, achieving an impressive 6%-16% increase in F1 scores, particularly when dealingwith FewRel with five unseen relations.
Anthology ID:
2024.findings-acl.446
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7510–7527
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.446/
DOI:
10.18653/v1/2024.findings-acl.446
Bibkey:
Cite (ACL):
Ting Xu, Haiqin Yang, Fei Zhao, Zhen Wu, and Xinyu Dai. 2024. A Two-Agent Game for Zero-shot Relation Triplet Extraction. In Findings of the Association for Computational Linguistics: ACL 2024, pages 7510–7527, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
A Two-Agent Game for Zero-shot Relation Triplet Extraction (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.446.pdf
PDF Search