Improving Recall for Hindi, Telugu, Oromo to English CLIR

Abstract

This paper presents the Cross Language Information Retrieval (CLIR) experiments of the Language Technologies Research Centre (LTRC, IIIT-Hyderabad) as part of our participation in the ad-hoc track of CLEF 2007. We present approaches to improve recall of query translation by handling morphological and spelling variations in source language keywords. We also present experiments using query expansion in CLIR using a source language monolingual corpus for Hindi, Telugu and English. We also present the effect of using an Oromo stemmer in Oromo-English CLIR system and report results using the CLEF 2007 dataset.

DOI: 10.1007/978-3-540-85760-0_13

Extracted Key Phrases

3 Figures and Tables

Cite this paper

@inproceedings{Pingali2007ImprovingRF, title={Improving Recall for Hindi, Telugu, Oromo to English CLIR}, author={Prasad Pingali and Kula Kekeba Tune and Vasudeva Varma}, booktitle={CLEF}, year={2007} }