DocAMR: Multi-Sentence AMR Representation and Evaluation

• Published in: arXiv.org
• Main Authors: Tahira Naseem, Blodgett, Austin, Kumaravel, Sadhana, O'Gorman, Tim, Young-Suk, Lee, Flanigan, Jeffrey, Ramón Fernandez Astudillo, Radu Florian, Roukos, Salim, Schneider, Nathan
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 06.05.2022
• Subjects: Algorithms; Annotations; Documents; Graph representations; Graphical representations; Graphs; Parsers
• ISSN: 2331-8422

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.