An Extended Query Performance Prediction Framework Utilizing Passage-Level Information

We show that document-level post-retrieval query performance prediction (QPP) methods are mostly suited for short query prediction tasks; such methods perform significantly worse in verbose (long and informative) query prediction settings. To address the prediction quality gap among query lengths, we propose a novel passage-level post-retrieval QPP framework. Our empirical analysis demonstrates that, those QPP methods that utilize passage-level information are much better suited for verbose QPP settings. Moreover, our proposed predictors, which utilize both document-level and passage-level information provide a more robust prediction which is less sensitive to query length.