Argument Inference from Relevant Event Mentions in Chinese Argument Extraction

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 1477–1487, Sofia, Bulgaria, August 4-9 2013. c⃝2013 Association for Computational Linguistics Argument Inference from Relevant Event Mentions in Chinese Argument Extraction Peifeng Li, Qiaoming Zhu, Guodong Zhou* School of Computer Science & Technology Soochow University, Suzhou, 215006, China {pfli, qmzhu, gdzhou}@suda.edu.cn Abstract As a paratactic language, sentence-level argument extraction in Chinese suffers much from the frequent occurrence of ellipsis with regard to inter-sentence arguments. To resolve such problem, this paper proposes a novel global argument inference model to explore specific relationships, such as Coreference, Sequence and Parallel, among relevant event mentions to recover those inter- sentence arguments in the sentence, discourse and document layers which represent the cohesion of an event or a topic. Evaluation on the ACE 2005 Chinese corpus justifies the effectiveness of our global argument inference model over a state-of-the-art baseline. 1 Introduction The task of event extraction is to recognize event mentions of a predefined event type and their arguments (participants and attributes). Generally, it can be divided into two subtasks: trigger extraction, which aims to identify trigger/event mentions and determine their event type, and argument extraction, which aims to extract various arguments of a specific event and assign the roles to them. In this paper, we focus on argument extraction in Chinese event extraction. While most of previous studies in Chinese event extraction deal with Chinese trigger extraction (e.g., Chen and Ji, 2009a; Qin et al., 2010; Li et al., 2012a, 2012b), there are only a few on Chinese argument extraction (e.g., Tan et al., 2008; Chen and Ji, 2009b). Following previous studies, we divide argument extraction into two components, argument identification and role determination, where the former recognizes the arguments in a specific event mention and the latter classifies these arguments by roles. With regard to methodology, most of previous studies on argument extraction recast it as a Semantic Role Labeling (SRL) task and focus on intra-sentence information to identify the arguments and their roles. However, argument extraction is much different from SRL in the sense that, while the relationship between a predicate and its arguments in SRL can be mainly decided from the syntactic structure, the relationship between an event trigger and its arguments are more semantics-based, especially in Chinese, as a paratactic (e.g., discourse-driven and pro-drop) language with the wide spread of ellipsis and the open flexible sentence structure. Therefore, some arguments of a specific event mention are far away from the trigger and how to recover those inter-sentence arguments becomes a challenging issue in Chinese argument extraction. Consider the following discourse (from ACE 2005 Chinese corpus) as a sample: D1: 巴勒斯坦自治政府否认和加沙走廊 20 号 清晨造成两名以色列人丧生(E1)的炸弹攻击 (E2)事件有关…表示将对这起攻击(E3)事件展 开调查 。(The Palestinian National Authority denied any involvement in the bomb attack (E2) occurred in the Gaza Strip on the morning of the 20th, which killed (E1) two Israelites. … They claimed that they will be investigating this attack (E3).) - From CBS20001120.1000.0823 In above discourse, there are three event mentions, one kill …

Content truncated to 500 words