Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability

TL;DR

This paper introduces WISeR, a new semantic representation that improves interpretability and applicability over AMR by replacing semantic role labels with thematic roles, leading to better parser performance.

Contribution

The paper proposes WISeR, a frameless semantic representation that enhances interpretability and parser learning efficiency compared to traditional AMR.

Findings

WISeR has higher inter-annotator agreement than AMR.

WISeR-trained parsers outperform AMR parsers in accuracy.

Beginners learn WISeR annotation faster.

Abstract

This paper presents a novel semantic representation, WISeR, that overcomes challenges for Abstract Meaning Representation (AMR). Despite its strengths, 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 that do not require reference to semantic frames. We create a new corpus of 1K English 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 more quickly. Finally, we train a state-of-the-art parser on the AMR 3.0 corpus and a WISeR corpus converted from AMR 3.0. The parser is evaluated on these corpora and our dialogue corpus. The WISeR model exhibits higher accuracy than its AMR counterpart across the board, demonstrating that WISeR is easier for parsers to learn.