Dynamic Information Retrieval Modeling for Domain-Specific Search

Abstract

Domain-specific search distinguishes itself from casual search in: (i) more complex and task-oriented information needs;(ii) use of a wider range of search strategies; (iii) requirement of a search session, rather than a one-shot query, to complete the complicated task; the search session often starts with a general query, follows by broadening or narrowing the search scope or drifting depending on the retrieved results, and continues this process until finding all aspects expected in the information need. These differences present new scientific challenges and call for more advanced domain-specific search algorithms. This research aims to create the next generation search engines, to be more specific, decision engines. The focus is on designing, experimenting, and deploying statistical models for modeling the dynamics presented in the search process.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2018
Accession Number
AD1051882

Entities

People

  • Grace H. Yang

Organizations

  • Georgetown University

Tags

Communities of Interest

  • Autonomy
  • Biomedical
  • Ground and Sea Platforms
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Computational Science
  • Data Mining
  • Game Theory
  • Hidden Markov Models
  • Information Retrieval
  • Information Science
  • Knowledge Management
  • Machine Learning
  • Natural Language Processing
  • Network Science
  • Probability
  • Probability Distributions
  • User Interface
  • Virtual Reality

Fields of Study

  • Computer science

Readers

  • Information Retrieval
  • Neural Network Machine Learning.
  • Strategic Security Studies

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval