Enhancing information retrieval using problem specific knowledge

  • Authors:
  • Nobuyuki Morioka;Ashesh Mahidadia

  • Affiliations:
  • School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia;School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia

  • Venue:
  • PKAW'06 Proceedings of the 9th Pacific Rim Knowledge Acquisition international conference on Advances in Knowledge Acquisition and Management
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the recent past, information retrieval techniques have improved significantly and it is now possible to access massive text corpora using some of the most popular search engine tools like Google, Yahoo, PubMed (popular search engine for medical literature), etc. Considering that such search engine tools are normally trying to retrieve information from massive text corpora, a number of search results they need to display might be in hundreds or even in tens of thousands. Normally it is not possible or practical to browse through a very large collection of search results, and often a typical user needs further assistance in focusing on the search results that might best meet his/her requirements. In this paper we present a new technique that allow a user to interactively express problem (task) specific knowledge (which is otherwise not possible using search engine tools like Google, Yahoo, PubMed, etc) and later use this knowledge to help a user to interactively and quickly focus on search results they might be interested in. The system presented in this paper integrates some of the techniques from the field of Natural Language Processing and Visualisation.