Incorporating user feedback to re-rank keyword search results

This paper capitalizes on user feedback of a keyword search engine to improve search performance on queries users are actively searching for. We assume users give a binary label as to whether a hypothesized token is correct. This signal is used to train a support vector machine to re-rank lattice posteriors using additional features derived from automatic speech recognition. We simulate user feedback using 1800 hours of English Fisher conversational telephone speech as a search corpus and the Switchboard corpus as our training corpus. Our novel contribution focuses on combining keyword specific and keyword independent models, improving search precision by 5% absolute over using one keyword independent model alone. Clustering keyword training data into multiple models based on their false alarm behavior gives even greater gains, achieving a 9% increase in precision over one keyword independent model.