English

DocAMR: Multi-Sentence AMR Representation and Evaluation

Computation and Language 2022-05-10 v2

Abstract

Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-document parsing into a unified graph representation lacks well-defined representation and evaluation. Taking advantage of a super-sentential level of coreference annotation from previous work, we introduce a simple algorithm for deriving a unified graph representation, avoiding the pitfalls of information loss from over-merging and lack of coherence from under-merging. Next, we describe improvements to the Smatch metric to make it tractable for comparing document-level graphs, and use it to re-evaluate the best published document-level AMR parser. We also present a pipeline approach combining the top performing AMR parser and coreference resolution systems, providing a strong baseline for future research.

Keywords

Cite

@article{arxiv.2112.08513,
  title  = {DocAMR: Multi-Sentence AMR Representation and Evaluation},
  author = {Tahira Naseem and Austin Blodgett and Sadhana Kumaravel and Tim O'Gorman and Young-Suk Lee and Jeffrey Flanigan and Ramón Fernandez Astudillo and Radu Florian and Salim Roukos and Nathan Schneider},
  journal= {arXiv preprint arXiv:2112.08513},
  year   = {2022}
}
R2 v1 2026-06-24T08:19:26.647Z