Semantic Role Labeling Improves Incremental Parsing

Ioannis Konstas; Frank Keller

doi:10.3115/v1/P15-1115

Semantic Role Labeling Improves Incremental Parsing

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

Abstract

Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsing, as incomplete input increases ambiguity. Intuitively, an incremental parser that has access to semantic information should be able to reduce ambiguity by ruling out semantically implausible analyses, even for incomplete input. In this paper, we test this hypothesis by combining an incremental TAG parser with an incremental semantic role labeller in a discriminative framework. We show a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F-score and in incremental F-score.

Original language	English
Title of host publication	Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Place of Publication	Beijing, China
Publisher	Association for Computational Linguistics
Pages	1191-1201
Number of pages	11
DOIs	https://doi.org/10.3115/v1/P15-1115
Publication status	Published - Jul 2015
Event	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing - Beijing, China Duration: 26 Jul 2015 → 31 Jul 2015 http://acl2015.org/

Conference

Conference	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing
Abbreviated title	ACL-IJCNLP 2015
Country	China
City	Beijing
Period	26/07/15 → 31/07/15
Internet address	http://acl2015.org/

Access to Document

10.3115/v1/P15-1115Licence: Creative Commons: Attribution (CC-BY)

Konstas Keller 2015 Semantic Role Labeling Improves Incemental ParsingAccepted author manuscript, 164 KB

http://aclweb.org/anthology/P15-1115 Licence: Creative Commons: Attribution (CC-BY)

1 Finished

An integrated model of syntactic and semantic prediction in human language processing
Keller, F. & Lapata, M.
EPSRC
15/09/11 → 28/02/15
Project: Research

Frank Keller
- frank.keller@ed.ed.ac.uk
- School of Informatics - Personal Chair in Computational Cognitive Science
- Institute of Language, Cognition and Computation
- Language, Interaction and Robotics
Person: Academic: Research Active

Cite this

Konstas, I., & Keller, F. (2015). Semantic Role Labeling Improves Incremental Parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (pp. 1191-1201). Association for Computational Linguistics. https://doi.org/10.3115/v1/P15-1115

@inproceedings{bf960b40ee03452396489a1eaafbf58d,

title = "Semantic Role Labeling Improves Incremental Parsing",

abstract = "Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsing, as incomplete input increases ambiguity. Intuitively, an incremental parser that has access to semantic information should be able to reduce ambiguity by ruling out semantically implausible analyses, even for incomplete input. In this paper, we test this hypothesis by combining an incremental TAG parser with an incremental semantic role labeller in a discriminative framework. We show a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F-score and in incremental F-score.",

author = "Ioannis Konstas and Frank Keller",

year = "2015",

month = jul,

doi = "10.3115/v1/P15-1115",

language = "English",

pages = "1191--1201",

booktitle = "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",

publisher = "Association for Computational Linguistics",

note = "53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

url = "http://acl2015.org/",

}

Konstas, I & Keller, F 2015, Semantic Role Labeling Improves Incremental Parsing. in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Beijing, China , pp. 1191-1201, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China, 26/07/15. https://doi.org/10.3115/v1/P15-1115

Semantic Role Labeling Improves Incremental Parsing. / Konstas, Ioannis; Keller, Frank.

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Beijing, China : Association for Computational Linguistics, 2015. p. 1191-1201.

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

TY - GEN

T1 - Semantic Role Labeling Improves Incremental Parsing

AU - Konstas, Ioannis

AU - Keller, Frank

PY - 2015/7

Y1 - 2015/7

N2 - Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsing, as incomplete input increases ambiguity. Intuitively, an incremental parser that has access to semantic information should be able to reduce ambiguity by ruling out semantically implausible analyses, even for incomplete input. In this paper, we test this hypothesis by combining an incremental TAG parser with an incremental semantic role labeller in a discriminative framework. We show a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F-score and in incremental F-score.

AB - Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsing, as incomplete input increases ambiguity. Intuitively, an incremental parser that has access to semantic information should be able to reduce ambiguity by ruling out semantically implausible analyses, even for incomplete input. In this paper, we test this hypothesis by combining an incremental TAG parser with an incremental semantic role labeller in a discriminative framework. We show a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F-score and in incremental F-score.

U2 - 10.3115/v1/P15-1115

DO - 10.3115/v1/P15-1115

M3 - Conference contribution

SP - 1191

EP - 1201

BT - Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

PB - Association for Computational Linguistics

CY - Beijing, China

T2 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing

Y2 - 26 July 2015 through 31 July 2015

ER -

Konstas I, Keller F. Semantic Role Labeling Improves Incremental Parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Beijing, China : Association for Computational Linguistics. 2015. p. 1191-1201 https://doi.org/10.3115/v1/P15-1115

Semantic Role Labeling Improves Incremental Parsing

Abstract

Conference

Access to Document

Fingerprint

Projects

An integrated model of syntactic and semantic prediction in human language processing

Profiles

Frank Keller

Cite this