Please use this identifier to cite or link to this item: doi:10.22028/D291-36147
Volltext verfügbar? / Dokumentlieferung
Title: AMR dependency parsing with a typed semantic algebra
Author(s): Groschwitz, Jonas
Lindemann, Matthias
Fowlie, Meaghan
Johnson, Mark
Koller, Alexander
Editor(s): Gurevych, Iryna
Miyao, Yusuke
Language: English
Title: The 56th Annual Meeting of the Association for Computational Linguistics - proceedings of the conference : July 15-20, 2018, Melbourne, Australia : ACL 2018, Volume 1: Long Papers
Startpage: 1831
Endpage: 1841
Publisher/Platform: Association for Computational Linguistics
Year of Publication: 2018
Title of the Conference: ACL 2018
Place of the conference: Melbourne, Australia
Publikation type: Conference Paper
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.
DOI of the first publication: 10.18653/v1/P18-1170
URL of the first publication: https://aclanthology.org/P18-1170.pdf
Link to this record: hdl:20.500.11880/32917
http://dx.doi.org/10.22028/D291-36147
ISBN: 978-1-948087-32-2
Date of registration: 17-May-2022
Faculty: P - Philosophische Fakultät
Department: P - Sprachwissenschaft und Sprachtechnologie
Professorship: P - Prof. Dr. Alexander Koller
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.


Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.