Abstract
Conventional dialogue generating methods focus on generating fluent sentences in context, but insufficient consideration of speaker emotions. They often generate sentences with the same sentimental polarity of the speakers. Such that sentences are hard to change the mood or viewpoints of the speakers, i.e., from a negative mood to positive one, etc. In this paper, we propose a method to generate dialogue sentences to provide different viewpoints. To this end, we propose two novel concepts, polarity co-occurrence (P-Cooc) and modification co-occurrence (M-Cooc). P-Cooc is used to find aspects providing different and comfortable viewpoints, and M-Cooc is used to find proper modification terms to such that aspects. The experimental results demonstrate that our method could provide supplementary viewpoints to promote critical thinking.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this study, we use the hotel review data-set of Datafinity [18] as the corpus. There are 147,236 sentences in the data-set.
- 2.
We have 20 subjects in our experiment.
References
Ennis, R.H.: A logical basis for measuring critical thinking skills. Educ. Leadersh. 43(2), 44–48 (1985)
Scriven, M., Paul, R.: Critical thinking. In: The 8th Annual International Conference on Critical Thinking and Education Reform, CA (1987)
Hirayama, R., Kusumi, T.: Effect of critical thinking disposition on interpretation of controversial issues: evaluating evidences and drawing conclusions. Jpn. J. Educ. Psychol. 52(2), 186–198 (2004)
Kusumi, T., Matsuda, K.: Structure of media literacy supported by critical thinking attitude. In: The 71st Annual Convention of the Japanese Psychological Association, p. 1PM085. The Japanese Psychological Association (2007). (in Japanese)
Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)
Takayama, J., Arase, Y.: Chat response generation based on feature vocabulary prediction using pointwise mutual information. In: Japanese NLP Conference 2019, pp. 3–34 (2019)
Meguro, T., Sugiyama, H., Higashinaka, R., Minami, Y.: Building a conversational system based on the fusion of rule-based and stochastic utterance generation. In: The 28th Annual Conference of the Japanese Society for Artificial Intelligence (2014), p. 2M5OS20b2. The Japanese Society for Artificial Intelligence (2014). (in Japanese)
Rosser, R.J., Sturges, S.B.: Response generator for mimicking human-computer natural language conversation, 24 August 2010. US7783486B2
Vinyals, O., Le, Q.: A neural conversational model. arXiv preprint arXiv:1506.05869 (2015)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
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)
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)
Nio, L., Sakti, S., Neubig, G., Yoshino, K., Nakamura, S.: Neural network approaches to dialog response retrieval and generation. IEICE Trans. Inf. Syst. 99(10), 2508–2517 (2016)
Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Lubis, N., Sakti, S., Yoshino, K., Nakamura, S.: Positive emotion elicitation in chat-based dialogue systems. IEEE/ACM Trans. Audio Speech Lang. Process. 27(4), 866–877 (2019)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642 (2013)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Dataset in Datafiniti. https://data.world/datafiniti/hotel-reviews. Accessed 12 2020
Acknowledgements
This work is partly supported by MIC SCOPE (172307001, 201607008) and KAKENHI (19H04116).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yoshida, S., Ma, Q. (2020). Generating Dialogue Sentences to Promote Critical Thinking. In: Hartmann, S., Küng, J., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2020. Lecture Notes in Computer Science(), vol 12391. Springer, Cham. https://doi.org/10.1007/978-3-030-59003-1_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-59003-1_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59002-4
Online ISBN: 978-3-030-59003-1
eBook Packages: Computer ScienceComputer Science (R0)