AMR dependency parsing with a typed semantic algebra

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


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.
Anthology ID:
P18-1170
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1831–1841
Language:
URL:
https://aclanthology.org/P18-1170
DOI:
10.18653/v1/P18-1170
Bibkey:
Cite (ACL):
Jonas Groschwitz, Matthias Lindemann, Meaghan Fowlie, Mark Johnson, and Alexander Koller. 2018. AMR dependency parsing with a typed semantic algebra. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1831–1841, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
AMR dependency parsing with a typed semantic algebra (Groschwitz et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1170.pdf
Note:
 P18-1170.Notes.pdf
Presentation:
 P18-1170.Presentation.pdf
Video:
 https://aclanthology.org/P18-1170.mp4