SIGIR'98 papers: The Effects of Query Structure and Dictionary Setups in Dictionary-Based Cross-Language Information Retrieval

The Effects of Query Structure and Dictionary Setups in Dictionary-Based Cross-Language Information Retrieval


Ari Pirkola
Department of Information Studies, University of Tampere, P.O. Box 607, FIN-33101 Tampere, Finland


Abstract

In this study, the effects of query structure and various setups of translation dictionaries on the performance of cross-language information retrieval (CLIR) were tested. The document collection was a subset of the TREC collection, and as test requests the study used TREC's health related topics. The test system was the INQUERY retrieval system. The performance of translated Finnish queries against English documents was compared to the performance of original English queries against English documents. Four natural language query types and three query translation methods, using a general dictionary and a domain specific (= medical) dictionary, were studied. There was only a slight difference in performance between the original English queries and the best cross-language queries, i.e., structured queries with medical dictionary and general dictionary translation. The structuring of queries was done on the basis of the output of dictionaries.


SIGIR'98
24-28 August 1998
Melbourne, Australia.
sigir98@cs.mu.oz.au.