Search

The article discusses how the RSVP voice-recognition search engine enhances translation accuracy and speech recognition in question answering (QA). Topics covered include the fundamental problems that make speech-recognition technologies not completely practical, the noisy environments in common audio situations, and the progress made by speech recognition in the last 30 years. Also mentioned are the analysis of relevant database patterns, the ranking of candidate questions using information distance, and the use of the RSVP methodology to correct spelling mistakes and grammatical errors.

We present a novel language modeling approach to capturing the query reformulation behavior of Web search users. Based on a framework that categorizes eight different types of "user moves" (adding/removing query terms, etc.), we treat search sessions as sequence data and build n-gram language models to capture user behavior. We evaluated our models in a prediction task. The results suggest that useful patterns of activity can be extracted from user histories. Furthermore, by examining prediction performance under different order n-gram models, we gained insight into the amount of history/context that is associated with different types of user actions. Our work serves as the basis for more refined user models. [ABSTRACT FROM AUTHOR]

The SIGIR 2013 Workshop on Modeling User Behavior of Information Retrieval Evaluation brought together researchers interested in improving Cranfield-style evaluation of information retrieval through the modeling of user behavior. The workshop included two invited talks, ten short paper presentations, and breakout groups. Workshop participants brainstormed research questions of interest and formed breakout groups to explore these questions in greater depth. In addition to summarizing the invited talks and presentations, this report details the results of the breakout groups, which provide a set of research directions for the improvement of information retrieval evaluation. [ABSTRACT FROM AUTHOR]

The Web N-gram Workshop was held on July 23, 2010 in Geneva, Switzerland, in conjunction with the 33rd Annual ACM SIGIR Conference. The workshop brought together leaders in information retrieval and language modeling to discuss the challenges in information retrieval and how language modeling approaches may help address some of these challenges, with a focus on using n-gram model to help solve them. The workshop consisted of 1 invited talk, 1 tutorial, 1 panel, 10 refereed paper presentations along with discussion sessions built-in in the agenda. [ABSTRACT FROM AUTHOR]