Semantic Role Labeling via tree kernel joint inference

Alessandro Moschitti, Daniele Pighin, Roberto Basili

Research output: Chapter in Book/Report/Conference proceedingChapter

34 Citations (Scopus)

Abstract

Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.

Original languageEnglish
Title of host publicationProceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X
Pages61-68
Number of pages8
Publication statusPublished - 1 Dec 2006
Externally publishedYes
Event10th Conference on Computational Natural Language Learning, CoNLL-X - New York, NY, United States
Duration: 8 Jun 20069 Jun 2006

Other

Other10th Conference on Computational Natural Language Learning, CoNLL-X
CountryUnited States
CityNew York, NY
Period8/6/069/6/06

Fingerprint

Labeling
Semantics
semantics
Syntactics
Support vector machines
ranking
Experiments
experiment

ASJC Scopus subject areas

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

Cite this

Moschitti, A., Pighin, D., & Basili, R. (2006). Semantic Role Labeling via tree kernel joint inference. In Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X (pp. 61-68)

Semantic Role Labeling via tree kernel joint inference. / Moschitti, Alessandro; Pighin, Daniele; Basili, Roberto.

Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006. p. 61-68.

Research output: Chapter in Book/Report/Conference proceedingChapter

Moschitti, A, Pighin, D & Basili, R 2006, Semantic Role Labeling via tree kernel joint inference. in Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. pp. 61-68, 10th Conference on Computational Natural Language Learning, CoNLL-X, New York, NY, United States, 8/6/06.
Moschitti A, Pighin D, Basili R. Semantic Role Labeling via tree kernel joint inference. In Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006. p. 61-68
Moschitti, Alessandro ; Pighin, Daniele ; Basili, Roberto. / Semantic Role Labeling via tree kernel joint inference. Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006. pp. 61-68
@inbook{8fafce5ec0424034a6e59a7e099a7bc7,
title = "Semantic Role Labeling via tree kernel joint inference",
abstract = "Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.",
author = "Alessandro Moschitti and Daniele Pighin and Roberto Basili",
year = "2006",
month = "12",
day = "1",
language = "English",
pages = "61--68",
booktitle = "Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X",

}

TY - CHAP

T1 - Semantic Role Labeling via tree kernel joint inference

AU - Moschitti, Alessandro

AU - Pighin, Daniele

AU - Basili, Roberto

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.

AB - Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.

UR - http://www.scopus.com/inward/record.url?scp=84862274561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862274561&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:84862274561

SP - 61

EP - 68

BT - Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X

ER -