Separating Argument Structure from Logical Structure in AMR
This work addresses a limitation in AMR for natural language processing researchers, offering an incremental improvement by aligning it more closely with Discourse Representation Theory.
The paper tackled the problem of representing scope and quantifiers in Abstract Meaning Representation (AMR) by extending it with context indices and constraints, resulting in correct predictions for inferences involving negation and bound variables while preserving AMR's core predicate-argument structure.
The AMR (Abstract Meaning Representation) formalism for representing meaning of natural language sentences was not designed to deal with scope and quantifiers. By extending AMR with indices for contexts and formulating constraints on these contexts, a formalism is derived that makes correct prediction for inferences involving negation and bound variables. The attractive core predicate-argument structure of AMR is preserved. The resulting framework is similar to that of Discourse Representation Theory.