How much of UCCA can be predicted from AMR?

TL;DR

This paper investigates the extent to which UCCA structures can be predicted from AMR graphs using rule-based systems, highlighting challenges and potential for cross-framework semantic analysis.

Contribution

It introduces deterministic and non-deterministic graph rewriting systems to convert AMR to UCCA, providing a novel approach to compare semantic frameworks.

Findings

Built and evaluated two graph rewriting systems

Discovered ambiguities in rule-based conversion

Discussed future directions for semantic framework comparison

Abstract

In this paper, we consider two of the currently popular semantic frameworks: Abstract Meaning Representation (AMR)a more abstract framework, and Universal Conceptual Cognitive Annotation (UCCA)-an anchored framework. We use a corpus-based approach to build two graph rewriting systems, a deterministic and a non-deterministic one, from the former to the latter framework. We present their evaluation and a number of ambiguities that we discovered while building our rules. Finally, we provide a discussion and some future work directions in relation to comparing semantic frameworks of different flavors.