Few-Shot User Intent Detection and Response Selection for Conversational Dialogue System Using Deep Learning

Conversational dialogue systems (CDSs), also known as conversational agents, have made significant development in recent years, driven by advances in natural language processing, machine learning, and artificial intelligence techniques. As a result, CDSs have been implemented across various industries, including education, e-commerce, and customer service in messaging apps, websites, and mobile apps to engage with users through natural language. The primary objective of chatbots is to facilitate communication with people and make numerous repetitious tasks easier for humans. This thesis investigates the application of deep learning methodologies in enterprise CDSs to enhance interpretability, fostering user trust in decision-making processes. The contributions of this thesis include proposing example and description-driven approaches that focus on the semantic similarities between the user input and the intent examples or descriptions in a topological tree for few-shot intent detection in enterprise CDSs. Moreover, this thesis presents a novel Topic-Aware Response Selection (TARS) model to retrieve the most suitable and coherent response from a set of candidates based on contextual information for users in persona-based CDSs.