Advertisement

Affective Neural Response Generation

  • Nabiha AsgharEmail author
  • Pascal Poupart
  • Jesse Hoey
  • Xin Jiang
  • Lili Mou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10772)

Abstract

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step in this direction by proposing three novel ways to incorporate affective/emotional aspects into long short term memory (LSTM) encoder-decoder neural conversation models: (1) affective word embeddings, which are cognitively engineered, (2) affect-based objective functions that augment the standard cross-entropy loss, and (3) affectively diverse beam search for decoding. Experiments show that these techniques improve the open-domain conversational prowess of encoder-decoder networks by enabling them to produce more natural and emotionally rich responses.

Keywords

Dialogue systems Human computer interaction Natural language processing Affective computing 

References

  1. 1.
    Asghar, N., Poupart, P., Jiang, X., Li, H.: Deep active learning for dialogue generation. In: Proceedings of Joint Conference on Lexical and Computational Semantics, pp. 78–83 (2017)Google Scholar
  2. 2.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)Google Scholar
  3. 3.
    Callejas, Z., Griol, D., López-Cózar, R.: Predicting user mental states in spoken dialogue systems. EURASIP J. Adv. Signal Process. 2011(1), 6 (2011)CrossRefGoogle Scholar
  4. 4.
    Danescu-Niculescu-Mizil, C., Lee, L.: Chameleons in imagined conversations: a new approach to understanding coordination of linguistic style in dialogs. In: Proceedings Workshop on Cognitive Modeling and Computational Linguistics, pp. 76–87 (2011)Google Scholar
  5. 5.
    Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378–382 (1971)CrossRefGoogle Scholar
  6. 6.
    Ghosh, S., Chollet, M., Laksana, E., Morency, L.P., Scherer, S.: Affect-LM: a neural language model for customizable affective text generation. In: ACL (2017)Google Scholar
  7. 7.
    Gimpel, K., Batra, D., Dyer, C., Shakhnarovich, G., Tech, V.: A systematic exploration of diversity in machine translation. In: EMNLP, pp. 1100–1111 (2013)Google Scholar
  8. 8.
    Hoey, J., Schröder, T., Alhothali, A.: Affect control processes: intelligent affective interaction using a partially observable markov decision process. Artif. Intell. 230, 134–172 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  10. 10.
    Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. In: NAACL-HLT, pp. 110–119 (2016)Google Scholar
  11. 11.
    Li, J., Monroe, W., Ritter, A., Jurafsky, D.: Deep reinforcement learning for dialogue generation. In: EMNLP, pp. 1192–1202 (2016)Google Scholar
  12. 12.
    Liu, C.W., Lowe, R., Serban, I., Noseworthy, M., Charlin, L., Pineau, J.: How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. In: EMNLP, pp. 2122–2132 (2016)Google Scholar
  13. 13.
    Malhotra, A., Yu, L., Schröder, T., Hoey, J.: An exploratory study into the use of an emotionally aware cognitive assistant. In: AAAI Workshop: Artificial Intelligence Applied to Assistive Technologies and Smart Environments (2015)Google Scholar
  14. 14.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)Google Scholar
  15. 15.
    Mou, L., Song, Y., Yan, R., Li, G., Zhang, L., Jin, Z.: Sequence to backward and forward sequences: a content-introducing approach to generative short-text conversation. In: COLING, pp. 3349–3358 (2016)Google Scholar
  16. 16.
    Osgood, C.E.: The nature and measurement of meaning. Psychol. Bull. 49(3), 197–237 (1952)CrossRefGoogle Scholar
  17. 17.
    Pennebaker, J.W., Francis, M.E., Booth, R.J.: Linguistic Inquiry and Word Count. Erlbaum Publishers, Mahwah (2001)Google Scholar
  18. 18.
    Pittermann, J., Pittermann, A., Minker, W.: Emotion recognition and adaptation in spoken dialogue systems. Int. J. Speech Technol. 13(1), 49–60 (2010)CrossRefGoogle Scholar
  19. 19.
    Robison, J., McQuiggan, S., Lester, J.: Evaluating the consequences of affective feedback in intelligent tutoring systems. In: Proceedings of International Conference on Affective Computing and Intelligent Interaction, pp. 1–6 (2009)Google Scholar
  20. 20.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: ACL, pp. 1577–1586 (2015)Google Scholar
  21. 21.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104–3112 (2014)Google Scholar
  22. 22.
    Vijayakumar, A.K., Cogswell, M., Selvaraju, R.R., Sun, Q., Lee, S., Crandall, D., Batra, D.: Diverse beam search: decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424 (2016)
  23. 23.
    Warriner, A.B., Kuperman, V., Brysbaert, M.: Norms of valence, arousal, and dominance for 13,915 English lemmas. Behav. Res. Methods 45(4), 1191–1207 (2013)CrossRefGoogle Scholar
  24. 24.
    Wen, T.H., Gasic, M., Mrkšić, N., Su, P.H., Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In: EMNLP, pp. 1711–1721 (2015)Google Scholar
  25. 25.
    Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1(6), 80–83 (1945)CrossRefGoogle Scholar
  26. 26.
    Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. arXiv preprint arXiv:1704.01074 (2017)

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Cheriton School of Computer ScienceUniversity of WaterlooWaterlooCanada
  2. 2.Noah’s Ark LabHuawei TechnologiesSha TinHong Kong

Personalised recommendations