Understanding combination of evidence using generative probabilistic models for information retrieval (abstract only)

Structured documents, rich information needs, and detailed information about users are becoming more pervasive within everyday computing usage. Applications such as Question Answering, reading tutors, and XML retrieval demand more robust retrieval on richly annotated documents. In order to effectively serve these applications, the community will need a better understanding of the combination of evidence. In this work, I propose that the use of simple generative probabilistic models will be an effective framework for these problems. Statistical language models, which are a special case of generative probabilistic models, have been used extensively within recent Information Retrieval research. Their flexibility has been very effective in adapting to numerous tasks and problems. I propose to extend the statistical language modeling framework to handle rich information needs and documents with structural and linguistic annotations. Much of the prior work on combination of evidence has had few well-studied theoretical contributions, so I also propose to develop a sounder theoretical basis which gives more predictable results.