A Weighted Boolean Model for Cross-Language Text Retrieval
Dictionary-based cross-language text retrieval systems must find a way to deal with the ambiguity associated with language translation. In this chapter, we claim that the use of conjunction in boolean models leads to simple, automatic disambiguation in the target language. We derive a new weighted boolean model based on probabilistic principles and test it on the cross-language text retrieval problem. The results suggest that while the weighted boolean model is highly effective in general retrieval situations, more experimental evidence needs to be gathered before we can state conclusively that it is particularly advantageous for cross-language applications. However, preliminary evidence suggests that the model is quite promising.
KeywordsMachine Translation Vector Model Query Term Query Expansion Vector Space Model
Unable to display preview. Download preview PDF.