A new multiword expression metric and its applications

  • Authors:
  • Fan Bu;Xiao-Yan Zhu;Ming Li

  • Affiliations:
  • Department of Computer Science and Technology, Tsinghua University, Beijing, China;Department of Computer Science and Technology, Tsinghua University, Beijing, China;David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada

  • Venue:
  • Journal of Computer Science and Technology - Special issue on natural language processing
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multiword Expressions (MWEs) appear frequently and ungrammatically in natural languages. Identifying MWEs in free texts is a very challenging problem. This paper proposes a knowledge-free, unsupervised, and language-independent Multiword Expression Distance (MED). The new metric is derived from an accepted physical principle, measures the distance from an n-gram to its semantics, and outperforms other state-of-the-art methods on MWEs in two applications: question answering and named entity extraction.