DeSRL: A linear-time semantic role labeling system

Massimiliano Ciaramita, Giuseppe Attardi, Felice Dell'Orletta, Mihai Surdeanu

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

13 Citations (Scopus)

Abstract

This paper describes the DeSRL system, a joined effort of Yahoo! Research Barcelona and Università di Pisa for the CoNLL-2008 Shared Task (Surdeanu et al., 2008). The system is characterized by an efficient pipeline of linear complexity components, each carrying out a different sub-task. Classifier errors and ambiguities are addressed with several strategies: revision models, voting, and reranking. The system participated in the closed challenge ranking third in the complete problem evaluation with the following scores: 82.06 labeled macro F1 for the overall task, 86.6 labeled attachment for syntactic dependencies, and 77.5 labeled F1 for semantic dependencies.

Original languageEnglish (US)
Title of host publicationCoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Pages258-262
Number of pages5
StatePublished - 2008
Externally publishedYes
Event12th Conference on Computational Natural Language Learning, CoNLL 2008 - Manchester, United Kingdom
Duration: Aug 16 2008Aug 17 2008

Other

Other12th Conference on Computational Natural Language Learning, CoNLL 2008
CountryUnited Kingdom
CityManchester
Period8/16/088/17/08

Fingerprint

Syntactics
Labeling
Macros
Classifiers
Pipelines
Semantics
semantics
voting
ranking
evaluation
time

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Ciaramita, M., Attardi, G., Dell'Orletta, F., & Surdeanu, M. (2008). DeSRL: A linear-time semantic role labeling system. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning (pp. 258-262)

DeSRL : A linear-time semantic role labeling system. / Ciaramita, Massimiliano; Attardi, Giuseppe; Dell'Orletta, Felice; Surdeanu, Mihai.

CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 258-262.

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

Ciaramita, M, Attardi, G, Dell'Orletta, F & Surdeanu, M 2008, DeSRL: A linear-time semantic role labeling system. in CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. pp. 258-262, 12th Conference on Computational Natural Language Learning, CoNLL 2008, Manchester, United Kingdom, 8/16/08.
Ciaramita M, Attardi G, Dell'Orletta F, Surdeanu M. DeSRL: A linear-time semantic role labeling system. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 258-262
Ciaramita, Massimiliano ; Attardi, Giuseppe ; Dell'Orletta, Felice ; Surdeanu, Mihai. / DeSRL : A linear-time semantic role labeling system. CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. pp. 258-262
@inproceedings{3b9954c86d314688a2e6e239ed459574,
title = "DeSRL: A linear-time semantic role labeling system",
abstract = "This paper describes the DeSRL system, a joined effort of Yahoo! Research Barcelona and Universit{\`a} di Pisa for the CoNLL-2008 Shared Task (Surdeanu et al., 2008). The system is characterized by an efficient pipeline of linear complexity components, each carrying out a different sub-task. Classifier errors and ambiguities are addressed with several strategies: revision models, voting, and reranking. The system participated in the closed challenge ranking third in the complete problem evaluation with the following scores: 82.06 labeled macro F1 for the overall task, 86.6 labeled attachment for syntactic dependencies, and 77.5 labeled F1 for semantic dependencies.",
author = "Massimiliano Ciaramita and Giuseppe Attardi and Felice Dell'Orletta and Mihai Surdeanu",
year = "2008",
language = "English (US)",
isbn = "1905593481",
pages = "258--262",
booktitle = "CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning",

}

TY - GEN

T1 - DeSRL

T2 - A linear-time semantic role labeling system

AU - Ciaramita, Massimiliano

AU - Attardi, Giuseppe

AU - Dell'Orletta, Felice

AU - Surdeanu, Mihai

PY - 2008

Y1 - 2008

N2 - This paper describes the DeSRL system, a joined effort of Yahoo! Research Barcelona and Università di Pisa for the CoNLL-2008 Shared Task (Surdeanu et al., 2008). The system is characterized by an efficient pipeline of linear complexity components, each carrying out a different sub-task. Classifier errors and ambiguities are addressed with several strategies: revision models, voting, and reranking. The system participated in the closed challenge ranking third in the complete problem evaluation with the following scores: 82.06 labeled macro F1 for the overall task, 86.6 labeled attachment for syntactic dependencies, and 77.5 labeled F1 for semantic dependencies.

AB - This paper describes the DeSRL system, a joined effort of Yahoo! Research Barcelona and Università di Pisa for the CoNLL-2008 Shared Task (Surdeanu et al., 2008). The system is characterized by an efficient pipeline of linear complexity components, each carrying out a different sub-task. Classifier errors and ambiguities are addressed with several strategies: revision models, voting, and reranking. The system participated in the closed challenge ranking third in the complete problem evaluation with the following scores: 82.06 labeled macro F1 for the overall task, 86.6 labeled attachment for syntactic dependencies, and 77.5 labeled F1 for semantic dependencies.

UR - http://www.scopus.com/inward/record.url?scp=84865084477&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865084477&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84865084477

SN - 1905593481

SN - 9781905593484

SP - 258

EP - 262

BT - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning

ER -