Discourse Representation Structure Parsing

Jiangming Liu; Shay Cohen; Maria Lapata

Discourse Representation Structure Parsing

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

Abstract

We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993). We propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages: basic DRS structure prediction, condition prediction (i.e., predicates and relations), and referent prediction (i.e., variables). Experimental results on the Groningen Meaning Bank (GMB) show that our model outperforms competitive baselines by a wide margin.

Original language	English
Title of host publication	56th Annual Meeting of the Association for Computational Linguistics
Place of Publication	Melbourne, Australia
Publisher	Association for Computational Linguistics (ACL)
Pages	429-439
Number of pages	11
Publication status	Published - Jul 2018
Event	56th Annual Meeting of the Association for Computational Linguistics - Melbourne Convention and Exhibition Centre, Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018 http://acl2018.org/

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2018
Country/Territory	Australia
City	Melbourne
Period	15/07/18 → 20/07/18
Internet address	http://acl2018.org/

Access to Document

discourse_representation_structure_parsing_acl2018Accepted author manuscript, 280 KB

http://aclweb.org/anthology/P18-1040 Licence: Creative Commons: Attribution (CC-BY)

TransModal: Translating from Multiple Modalities into Text
Lapata, M. (Principal Investigator)
EU government bodies
1/09/16 → 31/08/22
Project: Research
SUMMA - Scalable Understanding of Mulitingual Media
Renals, S. (Principal Investigator), Birch-Mayne, A. (Co-investigator) & Cohen, S. (Co-investigator)
EU government bodies
1/02/16 → 31/01/19
Project: Research

Cite this

@inproceedings{96c08df1f6e940dab87c4e35c8cf10bd,

title = "Discourse Representation Structure Parsing",

abstract = "We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993). We propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages: basic DRS structure prediction, condition prediction (i.e., predicates and relations), and referent prediction (i.e., variables). Experimental results on the Groningen Meaning Bank (GMB) show that our model outperforms competitive baselines by a wide margin.",

author = "Jiangming Liu and Shay Cohen and Maria Lapata",

year = "2018",

month = jul,

language = "English",

pages = "429--439",

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

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

note = "56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

url = "http://acl2018.org/",

}

Liu, J, Cohen, S & Lapata, M 2018, Discourse Representation Structure Parsing. in 56th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), Melbourne, Australia, pp. 429-439, 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Victoria, Australia, 15/07/18. <http://aclweb.org/anthology/P18-1040 >

TY - GEN

T1 - Discourse Representation Structure Parsing

AU - Liu, Jiangming

AU - Cohen, Shay

AU - Lapata, Maria

PY - 2018/7

Y1 - 2018/7

N2 - We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993). We propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages: basic DRS structure prediction, condition prediction (i.e., predicates and relations), and referent prediction (i.e., variables). Experimental results on the Groningen Meaning Bank (GMB) show that our model outperforms competitive baselines by a wide margin.

AB - We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993). We propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages: basic DRS structure prediction, condition prediction (i.e., predicates and relations), and referent prediction (i.e., variables). Experimental results on the Groningen Meaning Bank (GMB) show that our model outperforms competitive baselines by a wide margin.

M3 - Conference contribution

SP - 429

EP - 439

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

PB - Association for Computational Linguistics (ACL)

CY - Melbourne, Australia

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

Y2 - 15 July 2018 through 20 July 2018

ER -

Discourse Representation Structure Parsing

Abstract

Conference

Access to Document

Fingerprint

Projects

TransModal: Translating from Multiple Modalities into Text

SUMMA - Scalable Understanding of Mulitingual Media

Cite this