Advertisement

Open Domain Conversational Chatbot

  • Vibhashree DeshmukhEmail author
  • S. Jaya Nirmala
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1025)

Abstract

The main medium for communication between human beings is natural language in oral or textual form. Artificial Intelligent systems are supposed to be of use to humans such that they help in solving queries related to health, education, social and various other domains. Chatbots are faster and always available compared to traditional techniques of communication, ensuring quick and easy answers related to problems in different domains. The proposed solution implements a conversational chatbot using the seq2seq encoder-decoder model. The model is trained on a Twitter corpus containing conversational exchanges. The recurrent encoder-decoder performs the encoding of text conversations. RNN deals with sequential data which ideally captures the semantic summary of the input sequence and then based on context, the decoder generates output one word at a time step.

Keywords

Chatbot Open domain Conversational Generative Deep learning Twitter based 

References

  1. 1.
    Hussain, S., Ginge, A.: Extending a conventional chatbot knowledge base to external knowledge source and introducing user-based sessions for diabetes education. In: International Conference on Advanced Information Networking and Applications Workshops, vol. 30, no. 5, pp. 978–982, 23 July (2018)Google Scholar
  2. 2.
    Yan, Z., Duan, N., Bao, J., Chen, P., Zhou, M.: DocBot: an information retrieval approach for chatbot engines using unstructured documents. In: 54th Annual Meeting of the Association for Computational Linguistics, vol. 43, no. 8, pp. 516–525, 7 August (2016)Google Scholar
  3. 3.
    Bart, A., Spanakis, G.: A retrieval-based dialogue system utilizing utterance and context embeddings. In: 16th IEEE International Conference on Machine Learning & Applications, vol. 13, pp. 890–898, 18 Dec (2017)Google Scholar
  4. 4.
    Lamb, A.M., et al.: A new algorithm for training recurrent networks. In: Advances in Neural Information Processing Systems (2016)Google Scholar
  5. 5.
    Varghese, E., Rajappan Pillai, M.T.: A standalone generative conversational interface using deep learning. In: 2nd International Conference on Inventive Communication and Computational Technologies, pp. 1915–1920 (2018)Google Scholar
  6. 6.
    Sun, X., Chen, X., Pei, Z.: Emotional human-machine conversation generation based on seqGAN. In: 1st Asian conference on affective computing and intelligent interaction (2018)Google Scholar
  7. 7.
    Hingston, P.: A turing test for computer game bots. In: IEEE Transactions on, Computational Intelligence and AI in games, vol. 1, no 3, pp. 169–186 (2009)CrossRefGoogle Scholar
  8. 8.
    Higashinaka, R., Imamura, K., Meguro, T., Miyazaki, C., Kobayashi, N.: Towards an open domain conversational system fully based on natural language processing. In: Computational Linguistics and Chinese Language Processing (2014)Google Scholar
  9. 9.
    Ryu, P.-M., Jang, M.-G., Kim, H.-K.: Open domain question answering using Wikipedia-based knowledge model. In: Information Processing and Management, Elsevier, vol. 50, no. 2014, pp. 683–692 (2014)CrossRefGoogle Scholar
  10. 10.
    Ly, P., Kim, J.-H., Choi, C.-H., Lee, K.-H., Cho, W.-S.: Smart answering chatbot based on OCR and over generating transformations and ranking. In: 2016 Eighth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 1002–1005 (2016) Google Scholar
  11. 11.
    John, A.K., et al.: Legalbot: a deep learning-based conversational agent in the legal domain. In: Natural Language Processing and Information Systems. NLDB 2017, vol. 10260 (2017)CrossRefGoogle Scholar
  12. 12.
    Xu, A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer service on social media. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (2017)Google Scholar
  13. 13.
    Ghose, S., Barua, J.J.: Toward the implementation of a topic-specific dialogue based natural language chatbot as an undergraduate advisor. In: 2013 International Conference on Informatics, Electronics, and Vision, ICIEV (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.National Institute of TechnologyTrichyIndia

Personalised recommendations