Semantic Role Labeling via Integer Linear Programming Inference

Abstract

We present a system for the semantic role labeling task. The system combines a machine learning technique with an inference procedure based on integer linear programming that supports the incorporation of linguistic and structural constraints into the decision process. The system is tested on the data provided in CoNLL-2004 shared task on semantic role labeling and achieves very competitive results.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA460359

Entities

People

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

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy
  • C4I

DTIC Thesaurus Topics

  • Boundaries
  • Computer Languages
  • Computer Programming
  • Computer Science
  • Filters
  • Integer Programming
  • Language
  • Linear Programming
  • Machine Learning
  • Machines
  • Natural Languages
  • Neural Networks
  • Optimization
  • Reasoning
  • Recognition
  • Supervised Machine Learning
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Instructional Design and Training Evaluation.
  • Operations Research

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Learning Algorithms