ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Data driven methods for utterance semantic tagging

Ding Liu, Anthea Cheung, Anna Margolis, Patrick Redmond, Jun-won Suh, Chao Wang

The proliferation of mobile devices, along with advances in speech and natural language processing technologies, have given birth to a new wave of personal assistance applications that enable users to quickly and more naturally perform many tasks through voice on their smart devices. This paper focuses on a natural language understanding (NLU) solution for one such application. We adopted a data-driven approach, aiming to take advantage of large volume of deployment data for continued learning and system improvement. In this paper, we compare two different statistical models . a hidden Markov model and a maximum entropy Markov model . for the task of semantic slot extraction, and we present empirical results on real user data.

Cite as: Liu, D., Cheung, A., Margolis, A., Redmond, P., Suh, J.-w., Wang, C. (2013) Data driven methods for utterance semantic tagging. Proc. Interspeech 2013, 2068-2070

  author={Ding Liu and Anthea Cheung and Anna Margolis and Patrick Redmond and Jun-won Suh and Chao Wang},
  title={{Data driven methods for utterance semantic tagging}},
  booktitle={Proc. Interspeech 2013},