An Improved Approach for Semantic Graph Composition with CCG
This work addresses incremental improvements in AMR parsing for natural language processing researchers, focusing on theoretical analysis to enhance transparency and robustness.
The paper tackles the challenge of deriving Abstract Meaning Representation (AMR) graphs from Combinatory Categorial Grammar (CCG) by defining new semantics for CCG combinators, such as relation-wise alternatives for application and composition, and a new semantics for type raising, to better handle AMR parsing, including eventive nouns.
This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysis of eventive nouns, which present a challenge for deriving AMR graphs. Our theoretical analysis will facilitate future work on robust and transparent AMR parsing using CCG.