Joint Event Extraction with Hierarchical Policy Network

Proceedings of the 28th International Conference on Computational Linguistics, pages 2653–2664 Barcelona, Spain (Online), December 8-13, 2020 2653 Joint Event Extraction with Hierarchical Policy Network Peixin Huang1 Xiang Zhao1,2,∗ Ryuichi Takanobu3 Zhen Tan1 Weidong Xiao1,2,∗ 1National University of Defense Technology, Changsha, China 2Collaborative Innovation Center of Geospatial Technology, Wuhan, China 3Tsinghua University, Beijing, China {huangpeixin15, xiangzhao, tanzhen08a, wdxiao}@nudt.edu.cn; gxly19@mails.tsinghua.edu.cn Abstract Most existing work on event extraction (EE) either follows a pipelined manner or uses a joint structure but is pipelined in essence. As a result, these efforts fail to utilize information inter- actions among event triggers, event arguments, and argument roles, which causes information redundancy. In view of this, we propose to exploit the role information of the arguments in an event and devise a Hierarchical Policy Network (HPNet) to perform joint EE. The whole EE pro- cess is fulfilled through a two-level hierarchical structure consisting of two policy networks for event detection and argument detection. The deep information interactions among the subtasks are realized, and it is more natural to deal with multiple events issue. Extensive experiments on ACE2005 and TAC2015 demonstrate the superiority of HPNet, leading to state-of-the-art perfor- mance and is more powerful for sentences with multiple events. 1 Introduction Event extraction (EE) plays an important role in various real-life applications, such as information re- trieval and news summarization (Glavas and Snajder, 2014; Daniel et al., 2003). It aims to discover events with triggers and their corresponding arguments. Typically, EE contains several subtasks: trigger identification, trigger classification, event argument identification, and argument role classification. Some researchers handle these subtasks in a pipelined manner, i.e., perform trigger prediction and then identify arguments in separate stages, assuming that gold standard entities are provided (McClosky et al., 2011; Chen et al., 2015; Nguyen and Grishman, 2018; Yang et al., 2019). However, this staged manner has no strategy to take advantage of the deeper information interactions among these subtasks, so the upstream and the downstream subtasks cannot interfere with each other to improve their decisions. Although there have been joint approaches which aim to build a joint extractor (Yang and Mitchell, 2016; Nguyen and Nguyen, 2019; Zhang et al., 2019), they still follow a pipelined framework by first jointly predicting entities and triggers, and then scanning every entity-event pair for arguments and argument roles. One of the same limitations they share is that they produce redundant entity-event pairs informa- tion, thus bringing in possible errors. Another is the mismatch between arguments and triggers when the sentence contains multiple events. For example, consider the following sentence: In Baghdad, a cameraman died when an American tank fired on the Palestine hotel. In this sentence, “cameraman” is not only a Victim argument of event Die (trigger “died”), but also a Target argument of event Attack (trigger “fired”). However, as “cameraman” is far away from the trigger “fired” in the sentence, the extractor may fail to identify “cameraman” as one argument for event Attack. In view of this, we propose a Hierarchical Policy Network (HPNet) …

Content truncated to 500 words