AMR Dependency Parsing with a Typed Semantic Algebra
This work addresses the challenge of AMR parsing for natural language processing applications, representing an incremental improvement with specific gains in accuracy.
The authors tackled the problem of parsing strings into Abstract Meaning Representation (AMR) graphs by developing a semantic parser that uses a typed semantic algebra to integrate compositional structure, achieving state-of-the-art accuracy and outperforming strong baselines.
We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph. This allows us to use standard neural techniques for supertagging and dependency tree parsing, constrained by a linguistically principled type system. We present two approximative decoding algorithms, which achieve state-of-the-art accuracy and outperform strong baselines.