iCLEF2005 at REINA-USAL : use of free on-line machinetranslation programs for Interactive cross-language questionanswering

Abstract

For the iCLEF experiment of CLEF 2005 at University of Salamanca, we have explored the use of free on-line machine translation (MT) programs for the interactive Cross-LanguageQuestion Answering process (CL-QA), in two aspects: query formulation and displaying information. Two question-document language pair have been used: Spanish-English and Spanish- French. We used the GOOGLE Linguistic Tools at http://translate.google.com for thetranslation between first language pair, and SYSTRANSBox at http://w3.systranbox.comfor the second. Our cross-language information retrieval system is a standard document retrieval system performing monolingual searches. Passages has been used rather completedocuments, but the possibility of examining the context of a passage is intentionally excluded, although it reduces accuracy. For each question-document pair two groups of users were constituteddepending if they have good or poor reading skills in document language. The use of on-line MT program for the translation of Spanish queries into document language obtains ahigh number of right answers for all groups, but better for Spanish-French pair groups, due to French is more closed language to Spanish than English, so the quality of the translationsbetween Spanish and French is better. For our interactive CL-QA experiment, few corrections of translations were necessary in general, fewer for French target language. The use of MT to translate passages from English/French into Spanish in the displayinginformation process seems not improve the accuracy of the system. We expected that poor reading skills groups should obtain very much accuracy using this possibility, but difference isscarce when they don t use it. In general, all users reported that the possibility of translation the passages is highly appreciated. More experiment must be carried out to achieve other conclusions.