Discriminative Reasoning for Document-level Relation Extraction

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1653–1663 August 1–6, 2021. ©2021 Association for Computational Linguistics 1653 Discriminative Reasoning for Document-level Relation Extraction Wang Xu1, Kehai Chen2 and Tiejun Zhao1 1Harbin Institute of Technology, Harbin, China 2National Institute of Information and Communications Technology, Kyoto, Japan xuwang@hit-mtlab.net, khchen@nict.go.jp, tjzhao@hit.edu.cn Abstract Document-level relation extraction (DocRE) models generally use graph networks to im- plicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity pair in a document. In this paper, we propose a novel discriminative reasoning framework to explicitly model the paths of these reasoning skills between each entity pair in this document. Thus, a discriminative reasoning network is designed to estimate the relation probability distribution of different reasoning paths based on the constructed graph and vectorized document contexts for each entity pair, thereby recognizing their relation. Experimental results show that our method outperforms the previous state-of-the- art performance on the large-scale DocRE dataset. The code is publicly available at https://github.com/xwjim/DRN. 1 Introduction Document-level relation extraction (DocRE) aims to extract relations among entities within a docu- ment which requires multiple reasoning skills (i.e., pattern recognition, logical reasoning, coreference reasoning, and common-sense reasoning) (Yao et al., 2019). Generally, the input document is constructed as a structural graph-based on syntactic trees, coreference or heuristics represent relation information between all entityto pairs (Nan et al., 2020; Zeng et al., 2020; Xu et al., 2021). Thus, graph neural networks are applied to the constructed structural graph to model these reasoning skills. After performing multi-hop graph convolution, the feature representations of two entities are concatenated to recognize their relation by the classifier, achieving state-of-the-art performance in the DocRE task (Zeng et al., 2020; Xu et al., 2021). However, it is yet to be seen Pattern Recognition: [1] Me Musical Nephews is a 1942 one-reel animated cartoon directed by Seymour Kenitel. Relation: publication_data Supporting Evidence: 1 Common-sense Reasoning: [1] William and Adelaide had four children. Relation: spouse Supporting Evidence: 1 Logical Reasoning: [1] Elias Brown (May 9, 1793– July 7, 1857) was a U.S. Representative from Maryland. [2] Born near Baltimore, Maryland, Brown attended the common schools. … [7] He died near Baltimore, Maryland, and is interred in a private cemetery near Eldersburg, Maryland. Relation: Country Supporting Evidence: 1,7 Coreference Reasoning: [1] Dwight Tillery is an American politician of the Democratic Party who is active in local politics of Cincinnati, Ohio. ... [3] He also holds a law degree from the University of Michigan Law School. Relation: educated_at Supporting Evidence: 1,3 Figure 1: An example of different reasoning types. Different reasoning types have different reasoning processing. whether modeling these reasoning skills implicitly is competitive with the intuitive reasoning skills between one entity pair in this document. Figure 1 shows four kinds of reasoning skills for entity pairs in the DocRE dataset (Yao et al., 2019). First, take two entity pairs {“Me Musical Nephews”, “1942”} and {“William”, “Adelaide”} as examples, the intra- sentence reasoning concerns about the …

Content truncated to 500 words