Extraction of shallow language patterns: an approximation of data oriented parsing

  • Authors:
  • Samuel W. K. Chan

  • Affiliations:
  • Dept of Decision Sciences, The Chinese University of Hong Kong, Hong Kong, China

  • Venue:
  • AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel approach to extracting shallow language patterns from text The approach makes use of an attributed string matching technique which is based on two major but complementary factors: lexical similarities and sentence structures The technique takes full advantage of a huge number of sentence patterns in a Treebank, while preserving robustness, with-out being bogged down into a complete linguistic analysis The ideas described are implemented and an evaluation of 5,000 Chinese sentences is examined in order to justify its statistical significances.