Semantic Role Labeling via tree kernel joint inference

Alessandro Moschitti, Daniele Pighin, Roberto Basili

Research output: Contribution to conferencePaper

35 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
Pages61-68
Number of pages8
Publication statusPublished - 1 Dec 2006
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

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. 61-68. Paper presented at 10th Conference on Computational Natural Language Learning, CoNLL-X, New York, NY, United States.