AIML and sequence-to-sequence models to build artificial intelligence chatbots: insights from a comparative analysis
Conference paper
Teckchandani, N., Santokhee, A. and Bekaroo, G. 2019. AIML and sequence-to-sequence models to build artificial intelligence chatbots: insights from a comparative analysis. Second International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM 2018). Mauritius 28 - 30 Nov 2018 Cham Springer. https://doi.org/10.1007/978-3-030-18240-3_30
Type | Conference paper |
---|---|
Title | AIML and sequence-to-sequence models to build artificial intelligence chatbots: insights from a comparative analysis |
Authors | Teckchandani, N., Santokhee, A. and Bekaroo, G. |
Abstract | A chatbot is a software that is able to autonomously communicate with a human being through text and due to its usefulness, an increasing number of businesses are implementing such tools in order to provide timely communication to their clients. In the past, whilst literature has focused on implementing innovative chatbots and the evaluation of such tools, limited studies have been done to critically comparing such conversational systems. In order to address this gap, this study critically compares the Artificial Intelligence Mark-up Language (AIML), and Sequence-to-Sequence models for building chatbots. In this endeavor, two chatbots were developed to implement each model and were evaluated using a mixture of glass box and black box evaluation, based on 3 metrics, namely, user’s satisfaction, the information retrieval rate, and the task completion rate of each chatbot. Results showed that the AIML chatbot ensured better user satisfaction, and task completion rate, while the Sequence-to-Sequence model had better information retrieval rate. |
Keywords | Sequence-to-Sequence model; AIML ; Chatbot; Conversational agents ; Artificial Intelligence; Recurrent Neural Network |
Research Group | Research Group on Development of Intelligent Environments |
Conference | Second International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM 2018) |
Proceedings Title | Smart and Sustainable Engineering for Next Generation Applications: Proceeding of the Second International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM 2018), November 28–30, 2018, Mauritius |
ISSN | 1876-1100 |
Electronic | 1876-1119 |
ISBN | |
Hardcover | 9783030182397 |
Electronic | 9783030182403 |
Publisher | Springer |
Place of publication | Cham |
Publication dates | |
Online | 09 May 2019 |
01 Jan 2019 | |
Publication process dates | |
Deposited | 14 May 2019 |
Accepted | 17 Aug 2018 |
Output status | Published |
Accepted author manuscript | |
Copyright Statement | This is a post-peer-review, pre-copyedit version of a paper published in Smart and Sustainable Engineering for Next Generation Applications. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-18240-3_30 |
Additional information | Paper published as: Teckchandani N., Santokhee A., Bekaroo G. (2019) AIML and Sequence-to-Sequence Models to Build Artificial Intelligence Chatbots: Insights from a Comparative Analysis. In: Fleming P., Lacquet B., Sanei S., Deb K., Jakobsson A. (eds) Smart and Sustainable Engineering for Next Generation Applications. ELECOM 2018. Lecture Notes in Electrical Engineering, vol 561. Springer, Cham |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-18240-3_30 |
Scopus EID | 2-s2.0-85065922408 |
Web of Science identifier | WOS:000503388300030 |
Language | English |
https://repository.mdx.ac.uk/item/88462
Download files
73
total views82
total downloads0
views this month2
downloads this month