Learning semantic parsers: a constraint handling rule approach

  • Authors:
  • Dulce Aguilar-Solis

  • Affiliations:
  • Logic and Functional Programming Group, Department of Computing Science, Simon Fraser University, Burnaby, B.C., Canada

  • Venue:
  • ICLP'06 Proceedings of the 22nd international conference on Logic Programming
  • Year:
  • 2006

Quantified Score

Hi-index 0.02

Visualization

Abstract

Semantic parsing is the process of mapping a natural language input into some structure representing its meaning. Even though this process is natural and smooth for human beings, it constitutes a huge problem for a machine. Semantic parsing is a challenging and interesting problem that has been severely understudied. Most of the research in natural language understanding has focused on shallow semantic analysis (i.e. word sense disambiguation, case-role analysis, etc). Previous approaches to semantic parsing are not robust enough or are limited in its applicability because they are applied to simple domains where semantic parsing reduces to filling slots on a frame.