Advertisement

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

  • Firas KassawatEmail author
  • Debanjan Chaudhuri
  • Jens Lehmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11503)

Abstract

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their end-to-end text generation functionality. Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input. The model provides an additional integration of user intent along with text generation, trained with multi-task learning paradigm along with an additional regularization technique to penalize generating the wrong entity as output. The model further incorporates a Knowledge Graph entity lookup during inference to guarantee the generated output is state-full based on the local knowledge graph provided. We finally evaluated the model using the BLEU score, empirical evaluation depicts that our proposed architecture can aid in the betterment of task-oriented dialogue system’s performance.

Keywords

Dialogue systems Knowledge graphs Joint embeddings Neural networks 

Notes

Acknowledgements

This work was partly supported by the European Union’s Horizon 2020 funded projects WDAqua (grant no. 642795) and Cleopatra (grant no. 812997) as well as the BmBF funded project Simple-ML.

References

  1. 1.
    Alsuhaibani, M., Bollegala, D., Maehara, T., Kawarabayashi, K.: Jointly learning word embeddings using a corpus and a knowledge base. PLoS ONE 13(3), e0193094 (2018)CrossRefGoogle Scholar
  2. 2.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
  3. 3.
    Chaudhuri, D., Kristiadi, A., Lehmann, J., Fischer, A.: Improving response selection in multi-turn dialogue systems by incorporating domain knowledge. In: Proceedings of the 22nd Conference on Computational Natural Language Learning, pp. 497–507 (2018)Google Scholar
  4. 4.
    Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. arXiv arXiv:1707.01476v6 (2018)
  5. 5.
    Dhingra, B., et al.: Towards end-to-end reinforcement learning of dialogue agents for information access. arXiv preprint arXiv:1609.00777 (2016)
  6. 6.
    Eric, M., Manning, C.D.: Key-value retrieval networks for task-oriented dialogue. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pp. 37–49. Association for Computational Linguistics, Saarbrucken, August 2017. http://www.aclweb.org/anthology/W17-366
  7. 7.
    Graves, A.: Generating sequences with recurrent neural networks (2015)Google Scholar
  8. 8.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  9. 9.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  10. 10.
    Kosovan, S., Lehmann, J., Fischer, A.: Dialogue response generation using neural networks with attention and background knowledge. In: Proceedings of the Computer Science Conference for University of Bonn Students (CSCUBS 2017) (2017). http://jens-lehmann.org/files/2017/cscubs_dialogues.pdf
  11. 11.
    Liu, B., Lane, I.: Attention-based recurrent neural network models for joint intent detection and slot filling. arXiv preprint arXiv:1609.01454 (2016)
  12. 12.
    Liu, C.W., Lowe, R., Serban, I.V., Noseworthy, M., Charlin, L., Pineau, J.: How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:1603.08023 (2016)
  13. 13.
    Lowe, R., Pow, N., Serban, I., Charlin, L., Pineau, J.: Incorporating unstructured textual knowledge sources into neural dialogue systems. In: Neural Information Processing Systems Workshop on Machine Learning for Spoken Language Understanding (2015)Google Scholar
  14. 14.
    Lowe, R., Pow, N., Serban, I., Pineau, J.: The Ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. CoRR abs/1506.08909 (2015). http://arxiv.org/abs/1506.08909
  15. 15.
    Luong, M.T., Sutskever, I., Le, Q.V., Vinyals, O., Zaremba, W.: Addressing the rare word problem in neural machine translation. In: Proceeding of Association for Computational Linguistics (2015)Google Scholar
  16. 16.
    Madotto, A., Wu, C.S., Fung, P.: Mem2Seq: effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1468–1478. Association for Computational Linguistics (2018). http://aclweb.org/anthology/P18-1136
  17. 17.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
  18. 18.
    Mohammed, A., Danushka, B., Takanori, M., Kenichi, K.: Jointly learning word embeddings using a corpus and a knowledge base. PLoS ONE 13(3), e0193094 (2018)CrossRefGoogle Scholar
  19. 19.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)Google Scholar
  20. 20.
    Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)Google Scholar
  21. 21.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: Proceedings of 53rd Annual Meeting of the Association for Computational Linguistics (2015)Google Scholar
  22. 22.
    Ultes, S., et al.: PyDial: a multi-domain statistical dialogue system toolkit. In: Proceedings of ACL 2017, System Demonstrations, pp. 73–78. Association for Computational Linguistics (2017). http://aclweb.org/anthology/P17-4013
  23. 23.
    Vinyals, O., Le, Q.: A neural conversational model. In: International Conference on Machine Learning: Deep Learning Workshop (2015)Google Scholar
  24. 24.
    Wen, T.H., et al.: A network-based end-to-end trainable task-oriented dialogue system. arXiv preprint arXiv:1604.04562 (2016)
  25. 25.
    Williams, J.D., Zweig, G.: End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning (2016)Google Scholar
  26. 26.
    Xiao, H., Huang, M., Meng, L., Xiaoyan, Z.: SSP: semantic space projection for knowledge graph embedding with text descriptions. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. State Key Lab. of Intelligent Technology and Systems (2017)Google Scholar
  27. 27.
    Xu, Z., Liu, B., Wang, B., Sun, C., Wang, X.: Incorporating loose-structured knowledge into LSTM with recall gate for conversation modeling. arXiv preprint arXiv:1605.05110 (2016)

Copyright information

© Springer Nature Switzerland AG 2019

Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

Authors and Affiliations

  • Firas Kassawat
    • 1
    Email author
  • Debanjan Chaudhuri
    • 1
    • 2
  • Jens Lehmann
    • 1
    • 2
  1. 1.Smart Data Analytics Group (SDA)University of BonnBonnGermany
  2. 2.Enterprise Information Systems DepartmentFraunhofer IAISBonnGermany

Personalised recommendations