HARD Experiment at Maryland: From Need Negotiation to Automated HARD Process

Abstract

Our aim of participating in this year's High Accuracy Retrieval from Documents (HARD) track is to explore the possibility of developing an automated HARD retrieval model by leveraging existing models and theories about information need negotiation in information science. The clarification questions we developed are related to four different aspects of search topic, and four different techniques were developed to fully use the information collected from the user through these questions. Our initial analysis of the results indicates that this is a promising approach.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA456302

Entities

People

  • Daqing He
  • Dina Demner-fushman

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Computer Science
  • Computers
  • Extraction
  • Feedback
  • Frequency
  • Governments
  • Information Science
  • Language
  • Maryland
  • Middle East
  • Natural Language Processing
  • Natural Languages
  • Negotiations
  • Precision
  • Specialists
  • Universities

Readers

  • Database Systems and Applications
  • Systems Analysis and Design