End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-oriented Dialog

Published in International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

[PDF]


@INPROCEEDINGS{dqmem8461426, 
  author={Chien-Sheng Wu and Andrea Madotto and Genta Winata and Pascale Fung}, 
  booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-Oriented Dialog}, 
  year={2018}, 
  pages={6154-6158}, 
  ISSN={2379-190X}, 
  month={April},
}

Abstract

In this paper, we propose an end-to-end Dynamic Query Memory Network (DQMemNN) with a delexicalization mechanism for task-oriented dialog systems. The added dynamic component enables memory networks to capture the dialog’s sequential dependencies by using a context-based query. Besides, the delexicalization mechanism reduces learning complexity and it alleviates the out-of-vocabulary entity problems. Experiments show that DQMemNN outper- forms original end-to-end memory network models on bAbI full-dialog task by 3.1% per-response and 39.3% per-dialog accuracy. In addition, the proposed framework achieves a promising average per-response accuracy of 99.7% and per- dialog accuracy of 97.8% without hand-crafted rules and features.