Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 4672–4682 August 1–6, 2021. ©2021 Association for Computational Linguistics 4672 Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction Kaiwen Wei1,2, Sun Xian1,2, Zequn Zhang∗1,2, Jingyuan Zhang1,2, Zhi Guo1,2 and Li Jin1,2 1Key Laboratory of Network Information System Technology, Aerospace Information Research Institute, Chinese Academy of Sciences 2School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences weikaiwen19@mails.ucas.ac.cn, zqzhang1@mail.ie.ac.cn Abstract Implicit Event Argument Extraction seeks to identify arguments that play direct or implicit roles in a given event. However, most prior works focus on capturing direct relations be- tween arguments and the event trigger. The lack of reasoning ability brings many challenges to the extraction of implicit arguments. In this work, we present a Frame-aware Event Argu- ment Extraction (FEAE) learning framework to tackle this issue through reasoning in event frame-level scope. The proposed method lever- ages related arguments of the expected one as clues to guide the reasoning process. To bridge the gap between oracle knowledge used in the training phase and the imperfect related argu- ments in the test stage, we further introduce a curriculum knowledge distillation strategy to drive a final model that could operate without extra inputs through mimicking the behavior of a well-informed teacher model. Experimental results demonstrate FEAE obtains new state-of- the-art performance on the RAMS dataset. 1 Introduction In this work, we investigate the problem of Im- plicit Event Argument Extraction (IEAE) (Ebner et al., 2020), which seeks to identify arguments that play specific roles respect to a given trig- ger (Chen et al., 2020). Unlike previous event argument extraction task that only processes a sin- gle sentence, arguments in IEAE could span mul- tiple sentences. As shown in Figure 1, given a conflict/attack/firearmattack event triggered by the word shooting, an IEAE system is required to ex- tract four corresponding arguments with their roles in brackets: mass murder (target), firearms (instru- ment), Andrey Shpagonov (attacker), and Tatarstan (place). ∗Corresponding Author. The 1992 Tatarstan shooting was a mass murder. On 26 April 1992, 23-year-old Andrey Shpagonov, For Spain Tatarstan, hunting camp, April 26, 1992: 9 killed and 1 wounded. former huntsman went to a hunting camp. Example S1 S2 S3 S4 He went to steal firearms. S5 Confilict/attack/ firearmattack target place attacker instrument Figure 1: Instance of implicit event argument extraction on RAMS. Solid lines link the event trigger, event type, arguments, and argument roles. The dashed line connects two implicitly related arguments that could be inferred from each other. Mainstream methods to extract event arguments focus on learning pair-wise information between ar- guments and the given trigger. Chen et al. (2015a); Nguyen et al. (2016a); Liu et al. (2018); Sha et al. (2018) cast argument extraction as a relation classi- fication problem to extract pairs of trigger and can- didate arguments. Ebner et al. (2020); Zhang et al. (2020b) utilize event trigger as the …

Content truncated to 500 words