Implicitly-supervised learning in spoken language interfaces : an application to the confidence annotation problem

@inproceedings{Bohus2007ImplicitlysupervisedLI,
  title={Implicitly-supervised learning in spoken language interfaces : an application to the confidence annotation problem},
  author={Dan Bohus},
  year={2007}
}
In this paper we propose the use of a novel learning paradigm in spoken language interfaces – implicitly-supervised learning. The central idea is to extract a supervision signal online, directly from the user, from certain patterns that occur naturally in the conversation. The approach eliminates the need for developer supervision and facilitates online learning and adaptation. As a first step towards better understanding its properties, advantages and limitations, we have applied the proposed… CONTINUE READING