The limits of retrieval effectiveness

Authors:
Ronan Cummins;Mounia Lalmas;Colm O'Riordan
Affiliations:
School of Computing Science, University of Glasgow, UK and Dept. of Information Technology, National University of Ireland, Galway, Ireland;Yahoo! Research, Barcelona, Spain;Dept. of Information Technology, National University of Ireland, Galway, Ireland
Venue:
ECIR'11 Proceedings of the 33rd European conference on Advances in information retrieval
Year:
2011

Citing 5
Cited 2

Reducing long queries using query quality predictors

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Query sampling for ranking learning in web search

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Improvements that don't add up: ad-hoc retrieval results since 1998

Proceedings of the 18th ACM conference on Information and knowledge management
Automatic content linking: speech-based just-in-time retrieval for multimedia archives

Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Automatically generating queries for prior art search

CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments

Navigating the user query space

SPIRE'11 Proceedings of the 18th international conference on String processing and information retrieval
Query performance prediction for IR

SIGIR '12 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

Best match systems in Information Retrieval have long been one of the most predominant models used in both research and practice. It is argued that the effectiveness of these types of systems for the ad hoc task in IR has plateaued. In this short paper, we conduct experiments to find the upper limits of performance of these systems from three different perspectives. Our results on TREC data show that there is much room for improvement in terms of term-weighting and query reformulation in the ad hoc task given an entire information need.