AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite

Jonas Groschwitz, Shay B Cohen, Lucia Donatelli, Meaghan Fowlie

Submission Type: Regular Long Paper

Submission Track: Resources and Evaluation

Submission Track 2: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Keywords: evaluation, dataset, corpus, semantic parsing, AMR, sentence-level semantics, semantic graphs

TL;DR: We present an in-depth evaluation suite for AMR parsing that reveals abilities and shortcomings of current parsers

Abstract: We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics. AMR parsers now obtain high scores on the standard AMR evaluation metric Smatch, close to or even above reported inter-annotator agreement. But that does not mean that AMR parsing is solved; in fact, human evaluation in previous work indicates that current parsers still quite frequently make errors on node labels or graph structure that substantially distort sentence meaning. Here, we provide an evaluation suite that tests AMR parsers on a range of phenomena of practical, technical, and linguistic interest. Our 36 categories range from seen and unseen labels, to structural generalization, to coreference. GrAPES reveals in depth the abilities and shortcomings of current AMR parsers.

Submission Number: 4132