Generalized inference with multiple semantic role labeling systems

Peter Koomen, Vasin Punyakanok, Dan Roth, Wen Tau Yih

Research output: Contribution to conferencePaperpeer-review

Abstract

We present an approach to semantic role labeling (SRL) that takes the output of multiple argument classifiers and combines them into a coherent predicateargument output by solving an optimization problem. The optimization stage, which is solved via integer linear programming, takes into account both the recommendation of the classifiers and a set of problem specific constraints, and is thus used both to clean the classification results and to ensure structural integrity of the final role labeling. We illustrate a significant improvement in overall SRL performance through this inference.

Original languageEnglish (US)
Pages181-184
Number of pages4
DOIs
StatePublished - 2005
Event9th Conference on Computational Natural Language Learning, CoNLL 2005 - Ann Arbor, MI, United States
Duration: Jun 29 2005Jun 30 2005

Other

Other9th Conference on Computational Natural Language Learning, CoNLL 2005
Country/TerritoryUnited States
CityAnn Arbor, MI
Period6/29/056/30/05

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Generalized inference with multiple semantic role labeling systems'. Together they form a unique fingerprint.

Cite this