Modeling betweenness for question answering

  • Authors:
  • Brandeis Marshall

  • Affiliations:
  • Purdue University, West Lafayette, IN, USA

  • Venue:
  • ESAIR '10 Proceedings of the third workshop on Exploiting semantic annotations in information retrieval
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The gap between the user's information need and query is expanding due to the pervasiveness of Web search. Multimedia question answering is restricted by disjoint infrastructures of text, image, video and audio content. We address the construction and integration of multiple sources of related information. In particular, we consider the challenging information need of betweenness and defining it for any form of multimedia. We motivate betweenness definition using four questions and suggest k nearest neighbor as a first-step solution.