Semantic Role Labeling Via Generalized Inference Over Classifiers

Abstract

We present a system submitted to the CoNLL-2004 shared task for semantic role labeling. The system is composed of a set of classifiers and an inference procedure used both to clean the classification results and to ensure structural integrity of the final role labeling. Linguistic information is used to generate features during classification and constraints for the inference process. Semantic role labeling is a complex task to discover patterns within sentences corresponding to semantic meaning. We believe it is hopeless to expect high levels of performance from either purely manual classifiers or purely learned classifiers. Rather, supplemental linguistic information must be used to support and correct a learning system. The system we present here is composed of two phases.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA457895

Entities

People

  • Dan Roth
  • Dav Zimak
  • Vasin Punyakanok
  • Wen-tau Yih

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Applied Computer Science
  • Boundaries
  • Classification
  • Computational Linguistics
  • Computer Programming
  • Computer Science
  • Information Processing
  • Information Systems
  • Integer Programming
  • Language
  • Learning
  • Linear Programming
  • Linguistics
  • Machine Learning
  • Natural Languages
  • Reasoning
  • Structural Properties

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Computer Vision.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks