A unified optimization framework for robust pseudo-relevance feedback algorithms

We present a flexible new optimization framework for finding effective, reliable pseudo-relevance feedback models that unifies existing complementary approaches in a principled way. The result is an algorithmic approach that not only brings together different benefits of previous methods, such as parameter self-tuning and risk reduction from term dependency modeling, but also allows a rich new space of model search strategies to be investigated. We compare the effectiveness of a unified algorithm to existing methods by examining iterative performance and risk-reward tradeoffs. We also discuss extensions for generating new algorithms within our framework. Categories and Subject Descriptors: H.3.3 [Information Retrieval]: Retrieval Models General Terms: Algorithms, Experimentation

• Type: Journal
• Year: 2010
• Where: CIKM
• Authors: Joshua V. Dillon, Kevyn Collins-Thompson
• Keywords: Algorithms, CIKM 2010, Information Technology, Model Search Strategies, Reliable Pseudo-relevance Feedback