Abstract
Most of the current man-machine dialogues are at the two end-points of a spectrum of dialogues, i.e. goal-driven dialogues and non goal-driven chit-chats. Document-driven dialogues provide a bridge between them with the change of documents from structured data to unstructured free texts. This paper proposes a Document Driven Dialogue Generation model (D3G) which generates dialogues centering a given document, as well as answering user’s questions. A Doc-Reader mechanism is designed to locate the content related to user’s questions in documents. A Multi-Copy mechanism is employed to generate document-related responses. And the dialogue history is used in both mechanisms. Experimental results on the CMU_DOG dataset show that our D3G model can not only generate informative responses that are more relevant to the document, but also answer user’s questions better than the baseline models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Scenario1 contains 2128 conversations and Scenario 2 contains 1984 conversations.
- 2.
After many experiments, the results obtained by using the previous two utterances as dialogue history are the best.
- 3.
- 4.
We only use the Bleu-1 and ignore the brevity penalty. Moreover, we use nltk to calculate the BLEU and smooth it with SmoothingFunction().method2.
- 5.
We follow SEQ, only copy tokens from dialogue.
References
Cui, W., Xiao, Y., Wang, H., Song, Y., Wei, W.: KBQA: learning question answering over QA corpora and knowledge bases. Proc. VLDB Endow. 10(5), 565–576 (2017)
Ghazvininejad, M., et al.: A knowledge-grounded neural conversation model. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. Computer Science (2014)
Lavie, A., Agarwal, A.: METEOR: an automatic metric for MT evaluation with high levels of correlation with human judgments. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 228–231. Association for Computational Linguistics (2007)
Lei, W., Jin, X., Kan, M.Y., Ren, Z., He, X., Yin, D.: Sequicity: simplifying task-oriented dialogue systems with single sequence-to-sequence architectures. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 1437–1447 (2018)
Levin, E., Narayanan, S.S., Pieraccini, R., Zeljkovic, I.: Method of using a natural language interface to retrieve information from one or more data resources. AT & T (1999)
Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. arXiv preprint. arXiv:1510.03055 (2015)
Lian, R., Xie, M., Wang, F., Peng, J., Wu, H.: Learning to select knowledge for response generation in dialog systems (2019)
McTear, M.F.: Modelling spoken dialogues with state transition diagrams: experiences with the CSLU toolkit. In: Fifth International Conference on Spoken Language Processing (1998)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings Meeting of the Association for Computational Linguistics (2002)
See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks (2017)
Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension (2016)
Serban, I.V., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Vinyals, O., Le, Q.: A neural conversational model. Computer Science (2015)
Yang, Z., He, X., Gao, J., Li, D., Smola, A.: Stacked attention networks for image question answering (2016)
Young, S., Gasic, M., Thomson, B., Williams, J.D.: Pomdp-based statistical spoken dialog systems: a review. Proc. IEEE 101(5), 1160–1179 (2013)
Zhao, T., Lu, A., Lee, K., Eskenazi, M.: Generative encoder-decoder models for task-oriented spoken dialog systems with chatting capability (2017)
Zhou, H., Young, T., Huang, M., Zhao, H., Xu, J., Zhu, X.: Commonsense knowledge aware conversation generation with graph attention. In: IJCAI, pp. 4623–4629 (2018)
Zhou, K., Prabhumoye, S., Black, A.W.: A dataset for document grounded conversations (2018)
Zhu, C., Zeng, M., Huang, X.: SDNet: contextualized attention-based deep network for conversational question answering (2018)
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
Li, K., Bai, Z., Wang, X., Yuan, C. (2019). A Document Driven Dialogue Generation Model. In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics. CCL 2019. Lecture Notes in Computer Science(), vol 11856. Springer, Cham. https://doi.org/10.1007/978-3-030-32381-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-32381-3_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32380-6
Online ISBN: 978-3-030-32381-3
eBook Packages: Computer ScienceComputer Science (R0)