English

An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation

Computation and Language 2018-03-16 v2

Abstract

Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In this work, we address two of these limitations: ignoring positional information and a fixed number of possible response candidates. We propose to use positional encodings in the input to model the word order of the user utterances. Furthermore, by using a feedforward neural network, we are able to generate the output word by word and are no longer restricted to a fixed number of possible response candidates. Using the positional encoding, we were able to achieve better accuracies in the Dialog bAbI Tasks and using the feedforward neural network for generating the response, we were able to save computation time and space consumption.

Keywords

Cite

@article{arxiv.1803.02279,
  title  = {An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation},
  author = {Stefan Constantin and Jan Niehues and Alex Waibel},
  journal= {arXiv preprint arXiv:1803.02279},
  year   = {2018}
}

Comments

11 pages, 4 figures, forthcoming in IWSDS 2018; added quantitative analysis of sensitivity to modified user utterances and minor improvements

R2 v1 2026-06-23T00:44:04.197Z