How much of UCCA can be predicted from AMR?
This work addresses the challenge of interoperability between different semantic frameworks for NLP researchers, but it is incremental as it focuses on rule-based conversion without major breakthroughs.
The paper tackled the problem of predicting UCCA semantic annotations from AMR by building deterministic and non-deterministic graph rewriting systems, achieving results that revealed ambiguities and limitations in the conversion process.
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.