Abstract
Human conversations are often embedded with emotions. To simulate human conversations, the response generated by a chatbot not only has to be topically relevant to the post, but should also carry an appropriate emotion. In this paper, we conduct analysis based on social media data to investigate how emotions influence conversation generation. Based on observation, we propose methods to determine the appropriate emotions to be included in a response and to generate responses with the emotions. The encoder-decoder architecture is extended to incorporate emotions. We propose two implementations which train the two steps separately or jointly. An empirical study on a public dataset from STC at NTCIR-12 shows that our models outperform both a retrieval-based method and a generation model without emotion, indicating the importance of emotions in short text conversation generation and the effectiveness of our approach.
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.
- 2.
A flexible framework of neural networks for deep learning, http://chainer.org.
References
Asghar, N., Poupart, P., Hoey, J., Jiang, X., Mou, L.: Affective neural response generation. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 154–166. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-76941-7_12
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)
Cho, K., Merrienboer, B.V., Gülçehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724–1734 (2014)
Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs/1412.3555 (2014)
Colombo, P., Witon, W., Modi, A., Kennedy, J., Kapadia, M.: Affect-driven dialog generation. In: NAACL-HLT, pp. 3734–3743 (2019)
Ekman, P., Friesen, W.V., Ellsworth, P.: What emotion categories can observers judge from facial behavior? In: Emotion in the Human Face, pp. 67–75 (1972)
Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)
Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: NIPS, pp. 2042–2050 (2014)
Huang, C., Zaiane, O., Trabelsi, A., Dziri, N.: Automatic dialogue generation with expressed emotions. In: NAACL HLT, pp. 49–54 (2018)
Ji, Z., Lu, Z., Li, H.: An information retrieval approach to short text conversation. CoRR abs/1408.6988 (2014)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)
Lubis, N., Sakti, S., Yoshino, K., Nakamura, S.: Eliciting positive emotion through affect-sensitive dialogue response generation: a neural network approach. In: AAAI (2018)
Ritter, A., Cherry, C., Dolan, W.B.: Data-driven response generation in social media. In: EMNLP, pp. 583–593 (2011)
Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: ACL, pp. 1577–1586 (2015)
Shang, L., Sakai, T., Lu, Z., Li, H., Higashinaka, R., Miyao, Y.: Overview of the NTCIR-12 short text conversation task. In: Proceedings of NTCIR-12, pp. 473–484 (2016)
Sordoni, A., et al.: A neural network approach to context-sensitive generation of conversational responses. In: NAACL HLT, pp. 196–205 (2015)
Vinyals, O., Le, Q.: A neural conversational model. arXiv:1506.05869 (2015)
Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: EMNLP, pp. 606–615 (2016)
Yan, R., Song, Y., Wu, H.: Learning to respond with deep neural networks for retrieval-based human-computer conversation system. In: SIGIR, pp. 55–64 (2016)
Yuan, Z., Purver, M.: Predicting emotion labels for chinese microblog texts. In: Gaber, M.M., Cocea, M., Wiratunga, N., Goker, A. (eds.) Advances in Social Media Analysis. SCI, vol. 602, pp. 129–149. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18458-6_7
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv:1212.5701 (2012)
Zhang, M., Hurley, N.: Avoiding monotony: improving the diversity of recommendation lists. In: The 2nd ACM Conference on Recommender Systems (2008)
Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: AAAI (2018)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: ACL (2016)
Zhou, X., Wang, W.Y.: MojiTalk: generating emotional responses at scale. In: ACL, pp. 1128–1137 (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
Chen, Z. et al. (2019). Neural Response Generation with Relevant Emotions for Short Text Conversation. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11838. Springer, Cham. https://doi.org/10.1007/978-3-030-32233-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-32233-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32232-8
Online ISBN: 978-3-030-32233-5
eBook Packages: Computer ScienceComputer Science (R0)
