TREC 2001 Arabic/English Cross-Language IR track

Overview

The National Institute of Standards and Technology (NIST) will conduct an evaluation of Cross-Language Information Retrieval (CLIR) technology in conjunction with the Text Retrieval Conference (TREC-2001). The focus for 2001 will be retrieval of Arabic language newswire documents from topics in English or French. Additional information is available in the track guidelines.

Official Information

Track Guidelines: The track guidelines contain information about obtaining the test collection, running the experiments, and submitting the results.

Useful resources

Arabic IR and Computational Linguistics Resources: An extensive collection of links to resources that participants in the track might find useful.
Character set conversion: A Perl script provided by the LDC for converting the Arabic topic descriptions from ISO 8859-6 encoding to the UTF8 encoding that is used by the document collection for use in monolingual Arabic retrieval experiments. This script is freely redistributable.

Fred Gey

Doug Oard

Last modified: Fri Jul 20 01:09:47 2001