2017 AdversarialLearningforNeuralDia

From GM-RKB
(Redirected from Li et al., 2017)
Jump to navigation Jump to search

Subject Headings: Natural Language Generation Task.

Notes

Cited By

Quotes

Abstract

We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we jointly train two systems: a generative model to produce response sequences, and a discriminator - analogous to the human evaluator in the Turing test -” to distinguish between the human-generated dialogues and the machine-generated ones. In this generative adversarial network approach, the outputs from the discriminator are used to encourage the system towards more human-like dialogue. Further, we investigate models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines

References

BibTeX

@inproceedings{2017_AdversarialLearningforNeuralDia,
  author    = {Jiwei Li and
               Will Monroe and
               Tianlin Shi and
               Sebastien Jean and
               Alan Ritter and
               Dan Jurafsky},
  editor    = {Martha Palmer and
               Rebecca Hwa and
               Sebastian Riedel},
  title     = {Adversarial Learning for Neural Dialogue Generation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural
               Language Processing (EMNLP 2017)},
  address   = {Copenhagen, Denmark},
  pages     = {2157--2169},
  publisher = {Association for Computational Linguistics},
  year      = {2017},
  month     = {September},
  url       = {https://doi.org/10.18653/v1/d17-1230},
  doi       = {10.18653/v1/d17-1230},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2017 AdversarialLearningforNeuralDiaDaniel Jurafsky
Alan Ritter
Jiwei Li
Will Monroe
Tianlin Shi
Sebastien Jean
Adversarial Learning for Neural Dialogue Generation2017