Authors
Dilek Hakkani-Tür, Gokhan Tur, Rukmini Iyer, Larry Heck
Publication date
2012/3/25
Conference
2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Pages
4953-4956
Publisher
IEEE
Description
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. However, the form of natural language utterances occurring in spoken interactions with a computer differs stylistically from that of keyword search queries. In this paper, we propose a machine translation approach to learn a mapping from natural language utterances to search queries. We train statistical translation models, using task and domain independent semantically equivalent natural language and keyword search query pairs mined from the search query click logs. We then extend our previous work on enriching the existing classification feature sets for input utterance domain detection with features computed using the click distribution over a set of clicked URLs from search engine query click logs of user …
Scholar articles
DZ Hakkani-Tur, G Tur, R Iyer, LP Heck - US Patent 9,064,006, 2015
D Hakkani-Tür, G Tur, R Iyer, L Heck - 2012 IEEE International Conference on Acoustics …, 2012