Sequence to Sequence Model Performance for Education Chatbot

Abstract

Chatbot for education has great potential to complement human educators and education administrators. For example, it can be around the clock tutor to answer and clarify any questions from students who may have missed class. A chatbot can be implemented either by ruled based or artificial intel-ligence based. However, unlike the ruled-based chatbots, artificial intelli-gence based chatbots can learn and become smarter overtime and is more scalable and has become the popular choice for chatbot researchers recently. Recurrent Neural Network based Sequence-to-sequence (Seq2Seq) model is one of the most commonly researched model to implement artificial intelli-gence chatbot and has shown great progress since its introduction in 2014. However, it is still in infancy and has not been applied widely in educational chatbot development. Introduced originally for neural machine translation, the Seq2Seq model has been adapted for conversation modelling including question-answering chatbots. However, in-depth research and analysis of op-timal settings of the various components of Seq2Seq model for natural an-swer generation problem is very limited. Additionally, there has been no ex-periments and analysis conducted to understand how Seq2Seq model handles variations is questions posed to it to generate correct answers. Our experi-ments add to the empirical evaluations on Seq2Seq literature and provides insights to these questions. Additionally, we provide insights on how a cu-rated dataset can be developed and questions designed to train and test the performance of a Seq2Seq based question-answer model.

Rediscovering the use of chatbots in education: A systematic literature review

“…Aujogue and Aussem [3] described the training task (7,500 handmade synthetic dialogs) as laborious and after learning the chatbot brings benefits. Other chatbot implementations [40] should also be trained, proposing a set of questions and answers, where synonyms are established for identical questions or answers. However, some studies have proposed methodologies to simplify these tasks and improve the training process.…”

Trends & Methods in Chatbot Evaluation

“…x -- [17] 2016 --x [20] 2016 --x [50] 2016 -x - [34] 2016 x -- [2] 2016 -x x [78] 2016 x -x [58] 2016 --x [6] 2016 --x [22] 2017 -x x [77] 2017 x x - [39] 2017 x x - [60] 2017 x -- [21] 2017 -x - [63] 2017 x -- [76] 2017 x -- [54] 2017 x -- [79] 2017 --x [28] 2017 -x - [53] 2017 -x - [49] 2018 -x x [67] 2018 --x [51] 2018 -x x [52] 2018 x -- [59] 2018 -x x [44] 2018 -x x [42] 2018 -x x [19] 2018 -x x [71] 2018 -x x [8] 2018 -x x [35] 2018 x -- [31] 2018 -x x [72] 2018 -x x [13] 2019 -x x [41] 2019 -x - [45] 2019 x -- [11] 2019 --x [24] 2019 x x - [29] 2019 x x - [56] 2019 x -- [33] 2019 x -x [46] 2019 -x - [10] 2019 -x x [64] 2020 -x x [3] 2020 -x x [9] 2020 -x - [4] 2020 x -- [80] 2020 x x -…”

The Impact of Social Networks on the Development of Students’ Social Competence

“…Promising directions for providing communication between the participants of the learning process in a separate mode are chat bots [17], various programs, instant messaging tools (Telegram, Messenger, Viber), remote communication tools (Skype, Zoom), and mobile technologies [18]. They can provide either "one on one" communication mode or communication between a group of people; they can help in solving household and educational problems, and they can increase the social competence level.…”