Improving Event Detection with Abstract Meaning Representation

Event Detection (ED) aims to identify instances of specified types of events in text, which is a crucial component in the overall task of event extraction. The commonly used features consist of lexical, syntactic, and entity information, but the knowledge encoded in the Abstract Meaning Representation (AMR) has not been utilized in this task. AMR is a semantic formalism in which the meaning of a sentence is encoded as a rooted, directed, acyclic graph. In this paper, we demonstrate the effectiveness of AMR to capture and represent the deeper semantic contexts of the trigger words in this task. Experimental results further show that adding AMR features on top of the traditional features can achieve 67.8% (with 2.1% absolute improvement) F-measure (F1), which is comparable to the state-of-the-art approaches.