CLIP@UMD at SemEval-2016 task 8: Parser for abstract meaning representation using learning to search

Abstract

In this paper we describe our approach to the Abstract Meaning Representation (AMR) parsing shared task as part of SemEval 2016 We develop a novel technique to parse English sentences into AMR using Learning to Search. We decompose the AMR parsing task into three subtasks - that of predicting the concepts, the relations, and the root. Each of these subtasks are treated as a sequence of predictions. Using Learning to Search, we add pas predictions as features for future predictions and define a combined loss over the entire AMR structure.