Evaluating Domain Coverage in Low-Resource Generative Chatbots: A Comparative Study of Open-Domain and Closed-Domain Approaches Using BLEU Scores
Preprint
- 11 September 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
Chatbots employ Natural Language Processing (NLP) and Artificial Intelligence (AI) to conduct automated chats and provide online assistance to users. Chatbots fall into two categories—generative models and retrieval models. E-commerce is the main application for retrieval-based chatbots—which provide pre-programmed responses and are easy to use with controlled interactions. While generative-based chatbots are more appropriate for research applications—they are more difficult to train and maintain. This is because they produce unique responses based on large conversational datasets. Therefore, in order to establish whether open-domain or closed-domain techniques work better—this study examines the domain coverage of low-resource generative chatbots. We compare their performance using Bilingual Evaluation Understudy (BLEU) scores in different domains to determine which method performs better.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- From simulations to reality: enhancing multi-robot exploration for urban search and rescueInternational Journal of Information Technology, 2025
- Alternative agriculture land-use transformation pathways by partial-equilibrium agricultural sector model: a mathematical approachInternational Journal of Information Technology, 2024
- Exploring the Impact of Blockchain, AI, and ML on Financial Accounting Efficiency and Transformation2024
- Enhancing the predictive capability of a mathematical model for pseudomonas aeruginosa through artificial neural networksInternational Journal of Information Technology, 2024
- Predicting the Infection Level of COVID-19 Virus Using Normal Distribution-Based Approximation Model and PSO2023
- A comprehensive solution to retrieval-based chatbot constructionComputer Speech & Language, 2023
- An analysis of the robustness of UAV agriculture field coverage using multi-agent reinforcement learningInternational Journal of Information Technology, 2023
- Recent advances in deep learning based dialogue systems: a systematic surveyArtificial Intelligence Review, 2022
- Using Machine Learning to Quantify the Multimedia Risk Due to FuzzingMultimedia Tools and Applications, 2021
- Leveraging machine learning in the global fight against money laundering and terrorism financing: An affordances perspectiveJournal of Business Research, 2021