RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4985 - 4997 July 10-15, 2022 ©2022 Association for Computational Linguistics RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction Yuan Liang∗, Zhuoxuan Jiang∗, Di Yin and Bo Ren Tencent Cloud, China {ericyliang, alexzxjiang, endymecyyin, timren}@tencent.com Abstract In document-level event extraction (DEE) task, event arguments always scatter across sen- tences (across-sentence issue) and multiple events may lie in one document (multi-event issue). In this paper, we argue that the rela- tion information of event arguments is of great significance for addressing the above two is- sues, and propose a new DEE framework which can model the relation dependencies, called Relation-augmented Document-level Event Ex- traction (ReDEE). More specifically, this frame- work features a novel and tailored transformer, named as Relation-augmented Attention Trans- former (RAAT). RAAT is scalable to cap- ture multi-scale and multi-amount argument relations. To further leverage relation in- formation, we introduce a separate event re- lation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance. Extensive experi- ments demonstrate the effectiveness of the proposed method, which can achieve state-of- the-art performance on two public datasets. Our code is available at https://github. com/TencentYoutuResearch/RAAT. 1 Introduction Event extraction (EE) task aims to detect the event from texts and then extracts corresponding argu- ments as different roles, so as to provide a structural information for massive downstream applications, such as recommendation (Gao et al., 2016; Liu et al., 2017), knowledge graph construction (Wu et al., 2019; Bosselut et al., 2021) and intelligent question answering (Boyd-Graber and Börschinger, 2020; Cao et al., 2020). Most of the previous methods focus on sentence- level event extraction (SEE) (Ahn, 2006; Liao and Grishman, 2010; Li et al., 2013; Chen et al., 2015; Nguyen et al., 2016; Zhao et al., 2018; Sha et al., 2018; Yan et al., 2019; Du and Cardie, 2020; Li *These authors contributed equally to this work et al., 2020; Paolini et al., 2021; Lu et al., 2021), extracting events from a single sentence. However, SEE is mostly inconsistent with actual situations. For example, event arguments may scatter across different sentences. As illustrated in Figure 1, the event argument [ORG1] of event role Pledger is mentioned in Sentence 4 and the corresponding argument [ORG2] of event role Pledgee is in Sen- tence 5 and 6. We call this across-sentence issue. Another situation involves the multi-event issue, which means that multiple events may exist in the same document. As seen in the example in Fig- ure 1, where two event records coincide, we should recognize that they may partially share common arguments. Recently, document-level event extraction (DEE) attracts great attention from both academic and in- dustrial communities, and is regarded as a promis- ing direction to tackle the above issues (Yang et al., 2018; Zheng et al., 2019; Xu et al., 2021b; Yang et al., 2021; Zhu et al., 2021). However, by our observation, we discover that the …

Content truncated to 500 words