Extracting Subevents via an Effective Two-phase Approach

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 906–911, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Extracting Subevents via an Effective Two-phase Approach Allison Badgett and Ruihong Huang Texas A&M University {allisonbadgett, huangrh}@cse.tamu.edu Abstract We present our pilot research on automatically extracting subevents from a domain-specific corpus, focusing on the type of subevents that describe physical actions composing an event. We decompose the challenging problem and propose a two-phase approach that effectively captures sentential and local cues that describe subevents. We extracted a rich set of over 600 novel subevent phrases. Evaluation shows the automatically learned subevents help to dis- cover 10% additional main events (of which the learned subevents are a part) and improve event detection performance. 1 Introduction General and abstract event expressions and event keywords are often used for detecting events. To detect civil unrest events for example, common event expressions “took to the streets” and “staged a protest”, and event keywords “rally” and “strike” are usually considered as the first option. Subevents, events that occur as a part of the main event and therefore are useful to instantiate the main event, widely exist in event descriptions but they are rarely used for detecting the main event. In this paper, we focus on learning subevent phrases that describe physical actions composing an event. Such subevents are the evidence that an event is occurring. For example, if a person were to ex- plain how he knew that the crowd gathered in the street was rioting, he might point to the shouting of political slogans or tires lit on fire. In this instance, the riot would be the event. The slogan-shouting and tire-burning would be the subevents. Because subevent detection requires an understanding of lev- els of abstraction, this task can even be difficult for humans to perform. Furthermore, subevent phrases and general event phrases often have the same gram- matical structure and may share common words, which makes automatically differentiating between event phrases and subevent phrases within a docu- ment even more difficult. Additionally, events and subevents are not disjoint classes. There are some subevents that are unam- biguous. For example, “burning tires” is a concrete phrase that would not fall into the category of more abstract events. However, “gathered at site” is cer- tainly more ambiguous. Even human analysts would not necessarily agree on the appropriate class for this phrase. In many cases, the categorization would be context-dependent. Because of this, our research fo- cused on identifying the less ambiguous, and there- fore more concrete, cases. Instead of separating subevent phrases from gen- eral event phrases, we explicitly acquire subevent phrases by leveraging both sentential and local cues in describing subevents. We observed that subevents of the type in which we are interested, as impor- tant facts presented in news stories, are commonly mentioned in sentences that refer to the source of in- formation or simply in quotation sentences. These sentences usually start or end with characteristic phrases such …

Content truncated to 500 words