Dr. Yiming Yang 
Professor, Language Technologies Institute and Department of Machine Learning
Carnegie Mellon University

"Modeling Expected Utility of Multi-session Information Distillation"

Abstract:
An open challenge in information distillation is the evaluation and optimization of the utility of ranked lists with respect to flexible user interactions over multiple sessions. Utility depends on both the relevance and novelty of documents, and the novelty in turn depends on the user interaction history. However, user behavior is non-deterministic. We propose a new probabilistic framework for stochastic modeling of user behavior when browsing multi-session ranked lists, and a novel approximation method for efficient computation of the expected utility over numerous user-interaction patterns. Using this framework, we present the first utility-based evaluation over multi-session search scenarios, using the TDT4 corpus of news stories and compare a state-of-the-art distillation system against a relevance-based retrieval engine. We demonstrate that the distillation system obtains a 44% utility enhancement over the retrieval engine due to multi-session adaptive filtering, accurate novelty detection, and utility-based adjustment of ranked list lengths.

References (available at http://www-2.cs.cmu.edu/~yiming/publications.html)

Yiming Yang and Abhimanyu Lad. Modeling Expected Utility of Multi-session Information Distillation.
Second International Conference on the Theory of Information Retrieval (ICTIR09), 2009.

Yiming Yang, et al. Utility-based information distillation over temporally sequenced documents. SIGIR 2007: 31-38.

Biography:
Yiming Yang is a professor in the Language Technologies Institute and the Machine Learning Department within the School of Computer Science at Carnegie Mellon University. She received her Ph.D. in Computer Science from Kyoto University (Japan), and has been a faculty member at Carnegie Mellon University since 1996.
Her research has centered on statistical learning methods and their applications to a variety of challenging problems, including automated text categorization, information distillation based on both novelty detection and relevance assessment, joint modeling of heterogeneous sequentially interrelated tasks, user-centric adaptive and collaborative filtering, personalized email filtering and prioritization using social network analysis, and statistical learning from protein/gene expressions in micro-array data and tandem mass spectra, etc.