Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs

As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a string-to-string problem, and solve it in an unsupervised way. In this paper, we formalize it as a syntax-based alignment problem, and solve it in a supervised manner based on the syntax trees. Experiments verify the effectiveness of the proposed method.