SOTAVerified

AMR Parsing

Each AMR is a single rooted, directed graph. AMRs include PropBank semantic roles, within-sentence coreference, named entities and types, modality, negation, questions, quantities, and so on. See.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 117 papers

TitleStatusHype
Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based EncodingCode0
Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR ParsingCode0
Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parser—0
AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation SuiteCode0
AMR Parsing with Causal Hierarchical Attention and PointersCode0
Guiding AMR Parsing with Reverse Graph LinearizationCode0
Incorporating Graph Information in Transformer-based AMR ParsingCode0
AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR ParsingCode0
Slide, Constrain, Parse, Repeat: Synchronous SlidingWindows for Document AMR Parsing—0
AMR Parsing with Instruction Fine-tuned Pre-trained Language Models—0
Show:102550
← PrevPage 1 of 12Next →
All datasetsLDC2017T10LDC2014T12LDC2020T02LDC2015E86BioNew3The Little Prince

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1StructBART + MBSE (IBM)Smatch66.9—Unverified
2AMRBART largeSmatch63.2—Unverified
3Graphene SmatchSmatch62.8—Unverified
4SPRING DFSSmatch59.7—Unverified
5SPRING DFS + silverSmatch59.5—Unverified