SINAI at CLEF Ad-Hoc Robust Track 2007: Applying Google Search Engine for Robust Cross-Lingual Retrieval

Abstract

We report our web-based query generation experiments for English and French collections in the Robust task of the CLEF Ad-Hoc track. We continued with the approach adopted in the previous year, although the model has been modified. Last year we used Google to expand the original query. This year we create a new expanded query in addition to the original one. Thus, we retrieve two lists of relevant documents, one for each query (the original and the expanded one). In order to integrate the two lists of documents, we apply a logistic regression merging solution. The results obtained are discouraging but the failure analysis shows that very difficult queries are improved by using both queries instead of the original query. The problem is to decide when a query is very difficult.