Skip to main content

A Differentiable Generative Adversarial Network for Open Domain Dialogue

Part of the Lecture Notes in Electrical Engineering book series (LNEE,volume 714)

Abstract

This work presents a novel methodology to train open domain neural dialogue systems within the framework of Generative Adversarial Networks with gradient based optimization methods. We avoid the non-differentiability related to text-generating networks approximating the word vector corresponding to each generated token via a top-k softmax. We show that a weighted average of the word vectors of the most probable tokens computed from the probabilities resulting of the top-k softmax leads to a good approximation of the word vector of the generated token. Finally we demonstrate through a human evaluation process that training a neural dialogue system via adversarial learning with this method successfully discourages it from producing generic responses. Instead it tends to produce more informative and variate ones.

Keywords

  • Dialogue systems
  • Generative adversarial networks
  • Open domain dialogue

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-981-15-9323-9_24
  • Chapter length: 13 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   149.00
Price excludes VAT (USA)
  • ISBN: 978-981-15-9323-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   199.99
Price excludes VAT (USA)
Hardcover Book
USD   199.99
Price excludes VAT (USA)
Fig. 1
Fig. 2
Fig. 3

References

  1. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473

  2. Bengio S, Vinyals O, Jaitly N, Shazeer N (2015) Scheduled sampling for sequence prediction with recurrent neural networks. In: Advances in neural information processing systems, pp 1171–1179

    Google Scholar 

  3. Bengio Y, Léonard N, Courville A (2013) Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:13083432

  4. Bojanowski P, Grave E, Joulin A, Mikolov T (2016) Enriching word vectors with subword information. arXiv preprint arXiv:160704606

  5. Bowman SR, Vilnis L, Vinyals O, Dai AM, Jozefowicz R, Bengio S (2015) Generating sentences from a continuous space. arXiv preprint arXiv:151106349

  6. Ghazvininejad M, Brockett C, Chang MW, Dolan B, Gao J, Yih W, Galley M (2017) A knowledge-grounded neural conversation model. arXiv preprint arXiv:170201932

  7. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680

    Google Scholar 

  8. Honnibal M, Montani I (2017) Spacy 2: natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To appear

    Google Scholar 

  9. Hori T, Wang W, Koji Y, Hori C, Harsham B, Hershey JR (2019) Adversarial training and decoding strategies for end-to-end neural conversation models. Comput Speech Lang 54:122–139

    CrossRef  Google Scholar 

  10. Jang E, Gu S, Poole B (2016) Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:161101144

  11. Kannan A, Vinyals O (2017) Adversarial evaluation of dialogue models. arXiv preprint arXiv:170108198

  12. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:14126980

  13. Kusner MJ, Hernández-Lobato JM (2016) Gans for sequences of discrete elements with the gumbel-softmax distribution. arXiv preprint arXiv:161104051

  14. Li J, Monroe W, Shi T, Jean S, Ritter A, Jurafsky D (2017) Adversarial learning for neural dialogue generation. arXiv preprint arXiv:170106547

  15. Lison P, Tiedemann J (2016) Opensubtitles2016: extracting large parallel corpora from movie and tv subtitles. European language resources association

    Google Scholar 

  16. Lu J, Kannan A, Yang J, Parikh D, Batra D (2017) Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: Advances in neural information processing systems, pp 314–324

    Google Scholar 

  17. Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:150804025

  18. Maddison CJ, Mnih A, Teh YW (2016) The concrete distribution: a continuous relaxation of discrete random variables. arXiv preprint arXiv:161100712

  19. Serban IV, Sordoni A, Bengio Y, Courville AC, Pineau J (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. AAAI 16:3776–3784

    Google Scholar 

  20. Shetty R, Rohrbach M, Hendricks LA, Fritz M, Schiele B (2017) Speaking the same language: matching machine to human captions by adversarial training. In: Proceedings of the IEEE international conference on computer vision (ICCV)

    Google Scholar 

  21. Sordoni A, Galley M, Auli M, Brockett C, Ji Y, Mitchell M, Nie JY, Gao J, Dolan B (2015) A neural network approach to context-sensitive generation of conversation responses. arXiv preprint arXiv:150606714

  22. Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104–3112

    Google Scholar 

  23. Tuan YL, Lee HY (2019) Improving conditional sequence generative adversarial networks by stepwise evaluation. IEEE/ACM Trans Audio, Speech, Lang Process

    Google Scholar 

  24. Vinyals O, Le Q (2015) A neural conversational model. arXiv preprint arXiv:150605869

  25. Wu L, Xia Y, Zhao L, Tian F, Qin T, Lai J, Liu TY (2017) Adversarial neural machine translation. arXiv preprint arXiv:170406933

  26. Xu J, Ren X, Lin J, Sun X (2018) Diversity-promoting gan: A cross-entropy based generative adversarial network for diversified text generation. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 3940–3949

    Google Scholar 

  27. Yu L, Zhang W, Wang J, Yu Y (2017) Seqgan: sequence generative adversarial nets with policy gradient. In: AAAI, pp 2852–2858

    Google Scholar 

Download references

Acknowledgements

This work has been partially funded by the Basque Government under grant PRE_2017_1_0357, by the University of the Basque Country UPV/EHU under grant PIF17/310, and by the H2020 RIA EMPATHIC (Grant N: 769872).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Asier López Zorrilla .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

López Zorrilla, A., deVelasco Vázquez, M., Torres, M.I. (2021). A Differentiable Generative Adversarial Network for Open Domain Dialogue. In: Marchi, E., Siniscalchi, S.M., Cumani, S., Salerno, V.M., Li, H. (eds) Increasing Naturalness and Flexibility in Spoken Dialogue Interaction. Lecture Notes in Electrical Engineering, vol 714. Springer, Singapore. https://doi.org/10.1007/978-981-15-9323-9_24

Download citation

  • DOI: https://doi.org/10.1007/978-981-15-9323-9_24

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-15-9322-2

  • Online ISBN: 978-981-15-9323-9

  • eBook Packages: EngineeringEngineering (R0)