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
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
This is a fictitious example for explaining the algorithm, the scores are not what is being predicted from the real case scenarios.
- 2.
- 3.
We report these metrics for our best model and only for Mem2Seq because their implementation is open-source.
- 4.
References
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)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
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)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. arXiv arXiv:1707.01476v6 (2018)
Dhingra, B., et al.: Towards end-to-end reinforcement learning of dialogue agents for information access. arXiv preprint arXiv:1609.00777 (2016)
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
Graves, A.: Generating sequences with recurrent neural networks (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
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
Liu, B., Lane, I.: Attention-based recurrent neural network models for joint intent detection and slot filling. arXiv preprint arXiv:1609.01454 (2016)
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)
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)
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
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)
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
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)
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)
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)
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)
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)
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
Vinyals, O., Le, Q.: A neural conversational model. In: International Conference on Machine Learning: Deep Learning Workshop (2015)
Wen, T.H., et al.: A network-based end-to-end trainable task-oriented dialogue system. arXiv preprint arXiv:1604.04562 (2016)
Williams, J.D., Zweig, G.: End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning (2016)
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)
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)
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.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kassawat, F., Chaudhuri, D., Lehmann, J. (2019). Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning. In: Hitzler, P., et al. The Semantic Web. ESWC 2019. Lecture Notes in Computer Science(), vol 11503. Springer, Cham. https://doi.org/10.1007/978-3-030-21348-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-21348-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-21347-3
Online ISBN: 978-3-030-21348-0
eBook Packages: Computer ScienceComputer Science (R0)