UniNE at CLEF 2009: Persian Ad Hoc Retrieval and IP
Ljiljana Dolamic, Claire Fautsch, Jacques Savoy · CLEF (Working Notes) · 2009
This paper describes the participation of the University of Neuch^ atel to the CLEF 2008 evaluation campaign. In the Persian ad hoc task, we suggest using a light suxstripping algorithm for the Farsi language and the evaluations demonstrated that such an approach performs better than a simple light stemmer, an approach ignoring the stemming stage or a language independent approach (n-gram). The use of a blind query expansion (e.g., Rocchio’s model) may improve the retrieval eectiveness. Combining dierent indexing and search strategies may further enhance the corresponding MAP. In the Intellectual Property (IP) task, we try dierent strategies to select and weight pertinent words to be extracted from a patent description in order to form an eective query. We also evaluated dierent search models and found that probabilistic models tend to perform better than vector-space schemes.