A shortest-path method for arc-factored semantic role labeling

Xavier Lluís, Xavier Carreras, Lluis Marques

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles. Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures. Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.

Original languageEnglish
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages430-435
Number of pages6
ISBN (Print)9781937284961
Publication statusPublished - 2014
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: 25 Oct 201429 Oct 2014

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period25/10/1429/10/14

Fingerprint

Labeling
Semantics
Syntactics
Pipelines
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Lluís, X., Carreras, X., & Marques, L. (2014). A shortest-path method for arc-factored semantic role labeling. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 430-435). Association for Computational Linguistics (ACL).

A shortest-path method for arc-factored semantic role labeling. / Lluís, Xavier; Carreras, Xavier; Marques, Lluis.

EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 430-435.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lluís, X, Carreras, X & Marques, L 2014, A shortest-path method for arc-factored semantic role labeling. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 430-435, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 25/10/14.
Lluís X, Carreras X, Marques L. A shortest-path method for arc-factored semantic role labeling. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 430-435
Lluís, Xavier ; Carreras, Xavier ; Marques, Lluis. / A shortest-path method for arc-factored semantic role labeling. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 430-435
@inproceedings{536ab1a390d44889a75a19174a54bdaf,
title = "A shortest-path method for arc-factored semantic role labeling",
abstract = "We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles. Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures. Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.",
author = "Xavier Llu{\'i}s and Xavier Carreras and Lluis Marques",
year = "2014",
language = "English",
isbn = "9781937284961",
pages = "430--435",
booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - A shortest-path method for arc-factored semantic role labeling

AU - Lluís, Xavier

AU - Carreras, Xavier

AU - Marques, Lluis

PY - 2014

Y1 - 2014

N2 - We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles. Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures. Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.

AB - We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles. Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures. Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.

UR - http://www.scopus.com/inward/record.url?scp=84961346729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961346729&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284961

SP - 430

EP - 435

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -