QUT Para at TREC 2012 Web Track: Word Associations for Retrieving Web Documents

Abstract

Many existing information retrieval models do not explicitly take into account information about word associations. Our approach makes use of first and second order relationships found in natural language, known as syntagmatic and paradigmatic associations, respectively. This is achieved by using a formal model of word meaning within the query expansion process. On ad hoc retrieval, our approach achieves statistically significant improvements in MAP (0.158) and P at 20 (0.396) over our baseline model. The ERR at 20 and nDCG at 20 of our system was 0.249 and 0.192 respectively. Our results and discussion suggest that information about both syntagamtic and paradigmatic associations can assist with improving retrieval effectiveness on ad hoc retrieval.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2012
Accession Number
ADA581300

Entities

People

  • Bevan Koopman
  • Guido Zuccon
  • Mike Symonds
  • Peter David Bruza

Organizations

  • Queensland University of Technology

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Civil Rights
  • Computing-Related Activities
  • Data Sets
  • Electronic Mail
  • Information Operations
  • Information Retrieval
  • Information Systems
  • Language
  • Linguistics
  • Natural Languages
  • Standards
  • Training
  • Vocabulary

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Modeling and Simulation
  • Information Retrieval

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval