Baseline for Urdu IR evaluation

Authors:
Kashif Riaz
Affiliations:
University of Minnesota, Minneapolis, MN, USA
Venue:
Proceedings of the 2nd ACM workshop on Improving non english web searching
Year:
2008

Citing 4
Cited 0

Modern Information Retrieval

Modern Information Retrieval
A study in Urdu corpus construction

COLING '02 Proceedings of the 3rd workshop on Asian language resources and international standardization - Volume 12
TREC: Experiment and Evaluation in Information Retrieval (Digital Libraries and Electronic Publishing)

TREC: Experiment and Evaluation in Information Retrieval (Digital Libraries and Electronic Publishing)
Overview of the INEX 2007 Book Search track: BookSearch '07

ACM SIGIR Forum

Quantified Score

Hi-index	0.00

Visualization

Abstract

Goal of conferences like TREC, TIPSTER, NTCIR, CLEF is to judge the performance of different algorithms. Most of these conferences have tracks that deal with new and innovative information retrieval problems, but none has tackled to work with Urdu data, primarily because of the lack of resources. In this paper we present a baseline for Urdu IR evaluation along with resources necessary to do the task. The goal of this paper is to explore the strategy for creation of the test reference collection for Urdu Information Retrieval. A small test reference collection is presented composed of news articles from the Web along with some experiments to show its effectiveness.