Artificial Intelligence and Machine Learning can be cited as one of the greatest technological advancements in this century. They are revolutionizing the fields of computing, finance, healthcare, agriculture, space, tourism. Powerful models have achieved excellent performance on a myriad of complex learning tasks. One such product of AI is a chatbot. A chatbot is an intelligent software which can simulate a conversation with a user like a real human being. Chatbots have found their use in customer service, recommender systems, smart appliances, etc. Chatbots can be broadly divided into 2 types: Retrieval and Generative. Retrieval type chatbots are trained to provide the best fit answer from a database of predefined responses, whereas, generative type chatbots can generate the final answer from a training corpus. This paper proposes the design and implementation of a generative type travel chatbot using seq2seq model, which can generate answers to the user queries based on Kolkata tourism.

Chatbot, Machine Learning, Neural Network, Deep Learning, NLP

[1] J. Weizenbaum, “ELIZA - A Computer Program for the study of Natural Language Communication between Man and Machine”, Communications of the ACM, Vol.9, Issue.12, pp.36-45, 1966.
[2] T. Zemcik, “A Brief History of Chatbots”, In the Proceedings of International Conference on Artificial Intelligence, Control and Automation Engineering (AICAE 2019), China, pp.14-18, 2019.
[3] A. Mittal, A. Agarwal, A. Chouksey, R. Sriwas, S. Agrawal, “A Comparative Study of Chatbots and Humans”, International Journal of Advanced Research in Computer and Communication Engineering, Vol.5, Issue.3, pp.1055-1057, 2016.
[4] B. AbuShawar, E. Atwell, “ALICE Chatbot: Trials and Outputs”, Computacion y Sistemas, Vol.19, Issue.4, pp.625-632, 2015.
[5] M. Qiu, F. Li, S. Wang, X. Gao, Y. Chen, W. Zhao, H. Chen, J. Huang, W. Chu, “AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine”, In the Proceedings of the 55th Annual Meeting of the Association of Computational Linguistics, Canada, pp.498-503, 2017.
[6] M. Bandyopadhyay, M. Sahoo, M.L. Rangani, J.K. Mirji, “goTripper Chatbot for Tourism”, International Journal of Computer Sciences and Engineering, Vol.7, Special Issue.14, pp.36-40, 2019.
[7] B. Li, N. Jiang, J. Sham, H. Shi, H. Fazal, “Real-world Conversational AI for Hotel Bookings”, In the Proceedings of 2nd International Conference on Artificial Intelligence for Industries (AI4I 2019), USA, pp.58-62, 2019.
[8] S. Santhanam, S. Shaik, “A Survey of Natural Language Generation Techniques with a focus on Dialogue Systems – Past, Present and Future Directions”, CoRR, Vol.abs/1906.00500, 2019.
[9] F.S. Al-Anzi, D.M. AbuZeina, “A Survey of Markov Chain models in Linguistics Applications”, In the Proceedings of the 5th International Conference on Advanced Information Technologies and Applications (ICAITA 2016), UAE, pp.53-62, 2016.
[10] A. Sherstinsky, “Fundamentals of Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM) Network”, CoRR, Vol.abs/1808.03314, 2018.
[11] D. Varshney, A. Ekbal, G.P. Nagaraja, M. Tiwari, A.A.M. Gopinath, P. Bhattacharya, “Natural Language Generation using Transformer in an Open Domain Setting”, In the Proceedings of the 25th International Conference on Natural Language & Information Systems, Germany, pp.82-93, 2020.
[12] K. Cho, B.V. Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, “Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation”, In the Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), Qatar, pp.1724-1734, 2014.
[13] M. Dwarampudi, N.V. SubbaReddy, “Effects of padding on LSTMs and CNNs”, CoRR, Vol.abs/1903.07288, 2019.
[14] P. Mazare, S. Humeau, M. Raison, A. Bordes, “Training Millions of Personalized Dialogue Agents”, In the Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), Belgium, pp.2775-2779, 2018.
[15] P. Jayachandran, K. Nawas, C. Jackson, S. Ramanath, R. Prabhakaran, “Towards building a Neural Conversation Chatbot through Seq2Seq model”, International Journal of Scientific and Technology Research, Vol. 9, Issue.3, pp.1219-1222, 2020.
[16] G. Gnanaguru, “Programming a Chatbot in Python using Emotional Cognitive Conversational Agent Architecture (ECCAA)”, International Journal of Computer Sciences and Engineering, Vol.7, Issue.3, pp.510-516, 2019.
[17] Z.C. Lipton, J. Berkowitz, C. Elkan, “A critical review of Recurrent Neural Networks for sequence learning”, CoRR, Vol.abs/1506.00019, 2015.
[18] I. Sutskever, O. Vinyals, Q.V. Le, “Sequence to Sequence Learning with Neural Networks”, In the Proceedings of 28th International Conference on Neural Information Processing Systems (NeurIPS 2014), Canada, pp.3104-3112, 2014.
[19] S. Bengio, O. Vinyals, N. Jaitly, N. Shazeer, “A Scheduled Sampling for Sequence prediction with Recurrent Neural Networks”, In the Proceedings of 29th International Conference on Neural Information Processing Systems (NeurIPS 2015), Canada, pp.1171-1179, 2015.
[20] A. Lamb, A. Goyal, Y. Zhang, S. Zhang, A. Courville, and Y. Bengio, “Professor Forcing: A New Algorithm for training Recurrent Networks”, In the Proceedings of 30th International Conference on Neural Information Processing Systems (NeurIPS 2016), Spain, pp.4608-4616, 2016.