Document-Level Relation Extraction Based on Machine Reading Comprehension and Hybrid Pointer-sequence Labeling-Reference-Cited by-同舟云学术

Document-Level Relation Extraction Based on Machine Reading Comprehension and Hybrid Pointer-sequence Labeling

Published:2024-06-26 Issue:7 Volume:23 Page:1-16
ISSN:2375-4699
Container-title:ACM Transactions on Asian and Low-Resource Language Information Processing
language:en
Short-container-title:ACM Trans. Asian Low-Resour. Lang. Inf. Process.

Author:

wang xiaoyi¹^ORCID,Liu Jie²^ORCID,Wang Jiong³^ORCID,Duan Jianyong⁴^ORCID,guan guixia⁵^ORCID,zhang qing⁶^ORCID,Zhou Jianshe¹^ORCID

Affiliation:

1. China Language Intelligence Research Center, Capital Normal University, Beijing, China

2. School of Information Science and Technology, North China University of Technology, Beijing, China and China Language Intelligence Research Center, Capital Normal University, Beijing, China

3. College of Information Engineering, Capital Normal University, Beijing, China

4. School of Information Science and Technology, North China University of Technology, Beijing, China

5. School of Information Engineering, Capital Normal University, Beijing, China

6. School of Information Science and Technology, CNONIX National Standard Application and Promotion Laboratory,, North China University of Technology, Beijing, China

Abstract

Document-level relational extraction requires reading, memorization, and reasoning to discover relevant factual information in multiple sentences. It is difficult for the current hierarchical network and graph network methods to fully capture the structural information behind the document and make natural reasoning from the context. Different from the previous methods, this article reconstructs the relation extraction task into a machine reading comprehension task. Each pair of entities and relationships is characterized by a question template, and the extraction of entities and relationships is translated into identifying answers from the context. To enhance the context comprehension ability of the extraction model and achieve more precise extraction, we introduce large language models (LLMs) during question construction, enabling the generation of exemplary answers. Besides, to solve the multi-label and multi-entity problems in documents, we propose a new answer extraction model based on hybrid pointer-sequence labeling, which improves the reasoning ability of the model and realizes the extraction of zero or multiple answers in documents. Extensive experiments on three public datasets show that the proposed method is effective.

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

14th Five-Year Scientific Research Plan of the National language commission

Publisher

Association for Computing Machinery (ACM)

Link

https://dl.acm.org/doi/pdf/10.1145/3666042

Reference37 articles.

1. Kun Xu, Yansong Feng, Songfang Huang, and Dongyan Zhao. 2015. Semantic relation classification via convolutional neural networks with simple negative sampling. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 536–540.

2. Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. 2014. Relation classification via convolutional deep neural network. In Proceedings of the 25th International Conference on Computational Linguistics: Technical Papers (COLING’14). 2335–2344.

3. A Survey on Machine Reading Comprehension Systems

4. Hengzhu Tang, Yanan Cao, Zhenyu Zhang, Jiangxia Cao, Fang Fang, Shi Wang, and Pengfei Yin. 2020. HIN: Hierarchical inference network for document-level relation extraction. In Proceedings of the 24th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining (PAKDD’20), Part I 24. Springer, 197–209.

5. Difeng Wang, Wei Hu, Ermei Cao, and Weijian Sun. 2020. Global-to-local neural networks for document-level relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 3711–3721.