An Evolutive Knowledge Base for “AskBot” Toward Inclusive and Smart Learning-based NLP Techniques

Abstract

Intelligence chatbots have shown a growing interest in different domains including e-learning. They support learners by answering their repetitive and massive questions. In this paper, we develop a smart learning architecture for an inclusive chatbot handling both text and voice messages. Thus, disabled learners can easily use it. We automatically extract, preprocess, vectorize, and construct AskBot's Knowledge Base. The present work evaluates various vectorization techniques with similarity measures to answer learners' questions. The proposed architecture handles both Wh-Questions starting with Wh words and Non-Wh-Questions, beginning with unpredictable words. Regarding Wh-Questions, we develop a neural network model to classify intents. Our results show that the model's accuracy and the F1-Score are equal to 99,5%, and 97% respectively. With a similarity score of 0.6, our findings indicate that TF-IDF has performed well, correctly answering 90% of the tested Wh-Questions. Concerning No-Wh Questions, soft cosine measure, and fasttext successfully answered 72% of Non-Wh-Question.

Centralized Database Access: Transformer Framework and LLM/Chatbot Integration-Based Hybrid Model

“…The social robot generates explanations, asks questions, corrects errors, and gives answers based on a pre-trained GPT-3 model to explore the potential of generative language models for interactive learning with social robots at different levels of abstraction [8]. It is interesting to mention a chatbot that processes voice messages in addition to written communication, which is particularly practical for students with disabilities [9].…”