An Improved Approach for Semantic Graph Composition with CCG

TL;DR

This paper enhances CCG-based semantic parsing for AMR by introducing new combinator semantics, improving the derivation of AMR graphs, especially for complex constructions like eventive nouns.

Contribution

It proposes novel relation-wise combinator semantics and a new type raising semantics to improve AMR parsing with CCG.

Findings

Defines relation-wise combinators for better AMR graph derivation

Introduces new semantics for type raising in CCG

Provides analysis of eventive nouns in AMR parsing

Abstract

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.