Improving heuristic based temporal analysis of narratives with aspect determination

  • Authors:
  • Fel Song;Robin Cohen

  • Affiliations:
  • Dept. of Computing and Info Science, University of Guelph, Guelph, Ontario, Canada;Dept. of Computer Science, University of Waterloo, Waterloo, Ontario, Canada

  • Venue:
  • IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
  • Year:
  • 1995

Quantified Score

Hi-index 0.00

Visualization

Abstract

In previous work we presented an algorithm for tense interpretation which employs a temporal focus to determine the intended temporal relations between the states and events mentioned in a narrative In this paper, we propose a new two-phased classification scheme for aspect Each situation described in an utterance is first classified as static (state) or dynamic (event) and if dynamic as telic (event with a culmination point) or atelic (event without a culmination point) Then, independent of the class the view of the situation is identified either as a point or as an interval We then demonstrate how the determination of aspect can be integrated into our tense interpretation algorithm to produce a richer analysis of temporal relations Our classification for aspect is more detailed than most of the existing schemes allowing us to extract the interval relations between situations and cover a wide range of English narratives.