Recognizing speculative language in biomedical research articles: a linguistically motivated perspective

  • Authors:
  • Halil Kilicoglu;Sabine Bergler

  • Affiliations:
  • Concordia University, Montreal, Quebec, Canada;Concordia University, Montreal, Quebec, Canada

  • Venue:
  • BioNLP '08 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We explore a linguistically motivated approach to the problem of recognizing speculative language ("hedging") in biomedical research articles. We describe a method, which draws on prior linguistic work as well as existing lexical resources and extends them by introducing syntactic patterns and a simple weighting scheme to estimate the speculation level of the sentences. We show that speculative language can be recognized successfully with such an approach, discuss some shortcomings of the method and point out future research possibilities.