Employing web search query click logs for multi-domain spoken language understanding

Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Asli Celikyilmaz, Ashley Fidler, Dustin Hillard, Rukmini Iyer, Sarangarajan Parthasarathy
2011 2011 IEEE Workshop on Automatic Speech Recognition & Understanding  
Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically
more » ... from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances. 978-1-4673-0367-5/11/$26.00
doi:10.1109/asru.2011.6163968 dblp:conf/asru/Hakkani-TurTHCFHIP11 fatcat:7z35sldwxjeodlvhi6x5ybtnz4