Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability

Anonymous

Abstract: This paper presents a semantic representation called WISeR that overcomes challenges for Abstract Meaning Representation (AMR). Despite its richness and exapandability, AMR is not easily applied to languages or domains without predefined semantic frames, and its use of numbered arguments results in semantic role labels which are not directly interpretable and are semantically overloaded for parsers. We examine the numbered arguments of predicates in AMR and convert them to thematic roles which do not require reference to semantic frames. We create a new corpus of 1K dialogue sentences annotated in both WISeR and AMR. WISeR shows stronger inter-annotator agreement for beginner and experienced annotators, with beginners becoming proficient in WISeR annotation sooner. Finally, we train two state-of-the-art parsers on the AMR 3.0 corpus and a WISeR corpus converted from AMR 3.0. The parsers are evaluated on these corpora and our dialogue corpus. WISeR models exhibit higher accuracy than their AMR counterparts across the board, demonstrating that WISeR is easier for parsers to learn.