DeSRL: A linear-time semantic role labeling system

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

DeSRL: A linear-time semantic role labeling system

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

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

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 language	English (US)
Title of host publication	CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Pages	258-262
Number of pages	5
State	Published - 2008
Externally published	Yes
Event	12th Conference on Computational Natural Language Learning, CoNLL 2008 - Manchester, United Kingdom Duration: Aug 16 2008 → Aug 17 2008

Publication series

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

Other

Other	12th Conference on Computational Natural Language Learning, CoNLL 2008
Country/Territory	United Kingdom
City	Manchester
Period	8/16/08 → 8/17/08

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Linguistics and Language

Cite this

DeSRL: A linear-time semantic role labeling system. / Ciaramita, Massimiliano; Attardi, Giuseppe; Dell'Orletta, Felice et al.
CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 258-262 (CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning).

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

@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",

series = "CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning",

pages = "258--262",

booktitle = "CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning",

note = "12th Conference on Computational Natural Language Learning, CoNLL 2008 ; Conference date: 16-08-2008 Through 17-08-2008",

}

TY - GEN

T1 - DeSRL

T2 - 12th Conference on Computational Natural Language Learning, CoNLL 2008

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

T3 - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning

SP - 258

EP - 262

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

Y2 - 16 August 2008 through 17 August 2008

ER -

DeSRL: A linear-time semantic role labeling system

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this