Extracting Subevents via an Effective Two-phase Approach

Allison Badgett, Ruihong Huang
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
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 discover 10% additional main events (of which
more » ... e learned subevents are a part) and improve event detection performance.
doi:10.18653/v1/d16-1088 dblp:conf/emnlp/BadgettH16 fatcat:oi6fnbeeprei5fcy7pxp76n74q