AMR dependency parsing with a typed semantic algebra

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

doi:10.18653/v1/p18-1170

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 proceeding › Conference proceeding contribution › peer-review

50 Citations (Scopus)

71 Downloads (Pure)

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 language	English
Title of host publication	ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publication	Proceedings of the Conference, Vol. 1 (Long Papers)
Editors	Iryna Gurevych, Yusuke Miyao
Place of Publication	Stroudsburg PA
Publisher	Association for Computational Linguistics (ACL)
Pages	1831-1841
Number of pages	11
Volume	1
ISBN (Electronic)	9781948087322
DOIs	https://doi.org/10.18653/v1/p18-1170
Publication status	Published - 1 Jan 2018
Event	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/Territory	Australia
City	Melbourne
Period	15/07/18 → 20/07/18

Bibliographical note

Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Access to Document

10.18653/v1/p18-1170

Publisher version (open access)Final published version, 434 KBLicence: CC BY

Cite this

Groschwitz, J., Lindemann, M., Fowlie, M., Johnson, M., & Koller, A. (2018). AMR dependency parsing with a typed semantic algebra. In I. Gurevych, & Y. Miyao (Eds.), ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers) (Vol. 1, pp. 1831-1841). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-1170

Groschwitz, Jonas ; Lindemann, Matthias ; Fowlie, Meaghan et al. / AMR dependency parsing with a typed semantic algebra. ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). editor / Iryna Gurevych ; Yusuke Miyao. Vol. 1 Stroudsburg PA : Association for Computational Linguistics (ACL), 2018. pp. 1831-1841

@inproceedings{5cadf467151a4725bf364b3294c52320,

title = "AMR dependency parsing with a typed semantic algebra",

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.",

author = "Jonas Groschwitz and Matthias Lindemann and Meaghan Fowlie and Mark Johnson and Alexander Koller",

note = "Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.; 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

year = "2018",

month = jan,

day = "1",

doi = "10.18653/v1/p18-1170",

language = "English",

volume = "1",

pages = "1831--1841",

editor = "Iryna Gurevych and Yusuke Miyao",

booktitle = "ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

}

Groschwitz, J, Lindemann, M, Fowlie, M, Johnson, M & Koller, A 2018, AMR dependency parsing with a typed semantic algebra. in I Gurevych & Y Miyao (eds), ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). vol. 1, Association for Computational Linguistics (ACL), Stroudsburg PA, pp. 1831-1841, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15/07/18. https://doi.org/10.18653/v1/p18-1170

AMR dependency parsing with a typed semantic algebra. / Groschwitz, Jonas; Lindemann, Matthias; Fowlie, Meaghan et al.
ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). ed. / Iryna Gurevych; Yusuke Miyao. Vol. 1 Stroudsburg PA: Association for Computational Linguistics (ACL), 2018. p. 1831-1841.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - AMR dependency parsing with a typed semantic algebra

AU - Groschwitz, Jonas

AU - Lindemann, Matthias

AU - Fowlie, Meaghan

AU - Johnson, Mark

AU - Koller, Alexander

N1 - Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85063090720&partnerID=8YFLogxK

U2 - 10.18653/v1/p18-1170

DO - 10.18653/v1/p18-1170

M3 - Conference proceeding contribution

AN - SCOPUS:85063090720

VL - 1

SP - 1831

EP - 1841

BT - ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics

A2 - Gurevych, Iryna

A2 - Miyao, Yusuke

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg PA

T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018

Y2 - 15 July 2018 through 20 July 2018

ER -

Groschwitz J, Lindemann M, Fowlie M, Johnson M, Koller A. AMR dependency parsing with a typed semantic algebra. In Gurevych I, Miyao Y, editors, ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). Vol. 1. Stroudsburg PA: Association for Computational Linguistics (ACL). 2018. p. 1831-1841 doi: 10.18653/v1/p18-1170

AMR dependency parsing with a typed semantic algebra

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this