Effective Translation, Tokenization and Combination for Cross-Lingual Retrieval

Abstract

Our approach to cross-lingual document retrieval starts from the assumption that effective monolingual retrieval is at the core of any cross-language retrieval system. We devote particular attention to three crucial ingredients of our approach to cross-lingual retrieval. First, effective tokenization techniques are essential to cope with morphological variations common in many European languages. Second, effective combination methods allow us to combine the best of different strategies. Finally, effective translation methods for translating queries or documents turn a monolingual retrieval system into a cross-lingual retrieval system proper. The viability of our approach is shown by a series of experiments in monolingual, bilingual, and multilingual retrieval.