English

Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability

Computation and Language 2017-06-27 v1 Artificial Intelligence

Abstract

Generative encoder-decoder models offer great promise in developing domain-general dialog systems. However, they have mainly been applied to open-domain conversations. This paper presents a practical and novel framework for building task-oriented dialog systems based on encoder-decoder models. This framework enables encoder-decoder models to accomplish slot-value independent decision-making and interact with external databases. Moreover, this paper shows the flexibility of the proposed method by interleaving chatting capability with a slot-filling system for better out-of-domain recovery. The models were trained on both real-user data from a bus information system and human-human chat data. Results show that the proposed framework achieves good performance in both offline evaluation metrics and in task success rate with human users.

Keywords

Cite

@article{arxiv.1706.08476,
  title  = {Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability},
  author = {Tiancheng Zhao and Allen Lu and Kyusong Lee and Maxine Eskenazi},
  journal= {arXiv preprint arXiv:1706.08476},
  year   = {2017}
}

Comments

Accepted as a long paper in SIGIDIAL 2017

R2 v1 2026-06-22T20:29:55.340Z