Query Suggestions for Textual Problem Solution Repositories

Textual problem-solution repositories are available today in<br/>various forms, most commonly as problem-solution pairs from community<br/>question answering systems. Modern search engines that operate on<br/>the web can suggest possible completions in real-time for users as they<br/>type in queries. We study the problem of generating intelligent query<br/>suggestions for users of customized search systems that enable querying<br/>over problem-solution repositories. Due to the small scale and specialized<br/>nature of such systems, we often do not have the luxury of depending on<br/>query logs for finding query suggestions. We propose a retrieval model<br/>for generating query suggestions for search on a set of problem solution<br/>pairs. We harness the problem solution partition inherent in such<br/>repositories to improve upon traditional query suggestion mechanisms<br/>designed for systems that search over general textual corpora. We evaluate<br/>our technique over real problem-solution datasets and illustrate that<br/>our technique provides large and statistically significant