This paper describes two experiments in the domain of Cross Language Information Retrieval. Our basic approach is to translate queries word by word using machine readable dictionaries. The rst... Show moreThis paper describes two experiments in the domain of Cross Language Information Retrieval. Our basic approach is to translate queries word by word using machine readable dictionaries. The rst experiment compared different strategies to deal with word sense ambiguity: i) keeping all translations and integrate translation probabilitiesin the model, ii) a single translation is selected on the basis of the number of occurrences in the dictionary iii) word by word translation after word sense disambiguation in the source language. In a second experiment we constructed parallel corpora from web documents in order to construct bilingual dictionaries or improve translation probability estimates. We conclude that our best dictionary based CLIR approach is based on keeping all possible translations, not by simple substitution of a query term by its translations but by creating a structured query and including reverse translation probabilitiesin the retrieval model. Show less
