Ranking suspected answers to natural language questions using predictive annotation

  • Authors:
  • Dragomir R. Radev;John Prager;Valerie Samn

  • Affiliations:
  • University of Michigan, Ann Arbor, MI;TJ Watson Research Center, IBM Research Division, Hawthorne, NY;Columbia University, New York, NY

  • Venue:
  • ANLC '00 Proceedings of the sixth conference on Applied natural language processing
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we describe a system to rank suspected answers to natural language questions. We process both corpus and query using a new technique, predictive annotation, which augments phrases in texts with labels anticipating their being targets of certain kinds of questions. Given a natural language question, our IR system returns a set of matching passages, which we then rank using a linear function of seven predictor variables. We provide an evaluation of the techniques based on results from the TREC Q&A evaluation in which our system participated.