AMR dependency parsing with a typed semantic algebra

Jonas Groschwitz, Matthias Lindemann, Meaghan Fowlie, Mark Johnson, Alexander Koller

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph. This allows us to use standard neural techniques for supertagging and dependency tree parsing, constrained by a linguistically principled type system. We present two approximative decoding algorithms, which achieve state-of-the-art accuracy and outperform strong baselines.
Original languageEnglish
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics
Pages1831-1841
Number of pages11
ISBN (Print)9781948087322
DOIs
Publication statusPublished - 2018
Externally publishedYes

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Fingerprint

Dive into the research topics of 'AMR dependency parsing with a typed semantic algebra'. Together they form a unique fingerprint.

Cite this