In this paper, we report our experiments in the TREC 2008 Relevance Feedback Track. Our main goal is to study a novel problem in feedback, i.e., optimization of the balance of the query and feedback information. Intuitively, if we over-trust the feedback information, we may be biased to favor a particular subset of relevant documents, but undertrusting it would not take advantage of feedback. I...

We used clarification forms to study passage term feedback. When compared against pseudo-relevance feedback with an extremely large external corpus, we found that passage feedback resulted in a reduction in performance while term feedback significantly improved recall.

In HARD track of HARD 2005, we classify the 50 queries into 7 categories and make use of 3 kinds of feedback sources in various tasks. We find that the different kinds of queries perform differently in feedback tasks and the “CASE “ and “EVENT” queries are more sensitive to the feedback source. We also explore the internal structure of corpus and try to estimate the distribution of relevant doc...

WWW Video Search Engines have become increasingly commonplace within the last few years and at the same time video retrieval research has been receiving more attention with the annual TRECVid series of workshops. In this paper we evaluate methods of relevance feedback for video search engines operating over TV news data. We show for both video shots and TV news stories, that an optimal number o...