AN APPROACH FOR BUILDING A CHATBOT SYSTEM  FOR THE ADMISSION PROCESS OF DA LAT UNIVERSITY

Phan Thị Thanh Nga; Nguyễn Thị Lương; Tạ Hoàng Thắng; Thái Duy Quý

doi:10.34238/tnu-jst.6056

AN APPROACH FOR BUILDING A CHATBOT SYSTEM FOR THE ADMISSION PROCESS OF DA LAT UNIVERSITY

About this article

Received: 25/05/22 Revised: 22/08/22 Published: 23/08/22

Authors

1. Phan Thi Thanh Nga, Dalat University
2. Nguyen Thi Luong, Dalat University
3. Ta Hoang Thang, Dalat University
4. Thai Duy Quy , Dalat University

Abstract

A chatbot is a computer program designed for the chat interaction between robots and humans automatically using natural language techniques. This program is developed to be a virtual assistant which lures the human into the thought that they are talking to a real person. In this paper, we develop a chatbot system for the admission process of Da Lat university that allows the staff to answer questions immediately and automatically from users anytime. The important feature of any chatbot is to understand the user’s questions and to respond with appropriate answers. Our approach builds a chatbot application that adapts to the university's needs. We apply some BERT-based representation language models to predict the answer from the input question. The experimental results show that the salti/bert-base-multilingual-cased-finetuned-squad is a suitable model for our chatbot application since its F1 and EM scores for dev_set are remarkably high, accounting for 88.6% and 79.6%, respectively. For the intent classification, we achieve the accuracies of 99.9% and 100% for the validate accuracy and the test accuracy.

Keywords

Chatbot; Virtual assistant; BERT; University admission; Representation language models

Full Text:

PDF

References

[1] S. Hussain, O. A. Sianaki, and N. Ababneh, “A survey on conversational agents/chatbots classification and design techniques,” in Primate life histories, sex roles, and adaptability, U. Kalbitzer, A. M. Jack, and M. Katharine, Eds. Berlin: Springer, 2019, pp. 946-956.

[2] N. N. Khin and K. M. Soe, “University chatbot using artificial intelligence markup language,” in The IEEE Conference on Computer Applications (ICCA), Myanmar, 2020, pp. 103-107.

[3] D. Jacob, W. C. Ming, L. Kenton, and T. Kristina, “BERT: Pre-training of deep bidirectional transformers for language understanding,” Cornell University, October 11, 2018. [Online]. Available: https://arxiv.org/abs/1810.04805. [Accessed Apr. 28, 2020].

[4] B. R. Ranoliya, N. Raghuwanshi, and S. Singh, “Chatbot for university related FAQs,” in The 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), India, 2017, pp. 125-131.

[5] G. Hiremath, A. Hajare, P. Bhosale, and R. Nanaware, “Chatbot for education system,” International Journal of Advance Research in Technology, vol. 4, no. 3, pp. 37-43, 2020.

[6] A. Mondal, M. Dey, D. Das, S. Nagpal, and K. Garda, “Chatbot: An automated conversation system for the educational domain,” in The International Joint Symposium on Artificial Intelligence and Natural Language Processing, Thailand, 2018, pp. 103-109.

[7] T. N. Nguyen, and Q. D. Truong, “Support system for college admissions counseling,” (in Vietnamese), Can Tho University Journal of Science, no. 15, pp. 152-159, 2015.

[8] V. B. Nguyen, “Building a dialogue model for Vietnamese in the open domain based on the sequential learning method,” (in Vietnamese), MSC. Thesis, VNU Hanoi-University of Engineering and Technology, Hanoi, 2016.

[9] T. T. Nguyen, “Application of multi-class svm supervised learning algorithm in building a Vietnamese Q&A chatbot system,” (in Vietnamese), in The National scientific conference on IT and applications in various fields, Vietnam, 2018, pp. 98-105.

[10] M. T. Vi, V. M. Do, D. N. Tran, and T. A. Nguyen, “Building a Chatbot solution to support healthcare on Vietnamese domain,” (in Vietnamese), in The National Workshop on Application of High Technology in Practice, Vietnam, 2021, pp. 87-95.

[11] T. Mikolov, G. Corrado, K. Chen, and J. Dean, “Efficient estimation of word representations in vector space,” in The International Conference on Learning Representations, USA, 2013, pp. 202-210.

[12] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” Cornell University, October 16, 2013. [Online]. Available: https://arxiv.org/ abs/1310.4546. [Accessed Oct. 15, 2020].

[13] J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” in The Conference on empirical methods in natural language processing, Quatar, 2014, pp. 80-89.

[14] V. D. Le, “Vietnamese-stopwords,” March 15, 2019. [Online]. Available: https://github.com/ stopwords/vietnamese-stopwords. [Accessed April 25, 2020].

[15] V. T. Tran, “Python Vietnamese toolkit,” Pyvi 0.1.1, Jun 30, 2021. [Online]. Available: https://pypi.org/project/pyvi. [Accessed Sept. 20, 2021].

[16] H. Zhiheng, X. Peng, L, Davis, M. Ajay, and X. Bing, “TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding,” Cornell University, 2003. [Online]. Available: https://arxiv.org/abs/2003.07000. [Accessed Sept. 15, 2020].

[17] Q. D. Nguyen, and T. A. Nguyen, “PhoBERT: Pre-trained language models for Vietnamese,” Cornell University, 2020. [Online]. Available: https://arxiv.org/abs/1310.4546. [Accessed Dec. 19, 2020].

[18] D. Jin, Z. Jin, J. T. Zhou, and P. Szolovits, “Is bert really robust? a strong baseline for natural language attack on text classification and entailment,” in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 5, pp. 8018-8025, 2020.

[19] H. Zhiheng, X. Wei, and Y. Kai, “Bidirectional lstm-crf models for sequence tagging,” Cornell University, 2020. [Online]. Available: https://arxiv.org/abs/1508.019912015. [Accessed Dec. 19, 2020].

DOI: https://doi.org/10.34238/tnu-jst.6056

Refbacks

There are currently no refbacks.



Remember me