Dialog Generation with Conversational Agent in the Context of Task-Oriented using a Transformer Architecture

Abstract

The use of conversational agents has become increasingly popular in recent years due to their ability to mimic human-like interactions in Human Com puter Interaction (HCI) and provide personalized assistance to users. How ever, creating effective dialogues between humans and conversational agents remains a challenging task, particularly in the context of task-oriented ap plications. This is because such applications require agents to understand complex user requests and generate appropriate responses that take into ac count the user’s goals, preferences, and constraints.To address this challenge, we propose to adapt the LongT5 (Long Text-To-Text-Transfer Transformer) architecture, a transformer-based language processing model well known for its performance in a lot of Natural Language Processing (NLP) tasks. Then, to explore the use of the new proposed model named MegaT for generating task-oriented dialogues between conversational agents and human user. This involves designing and implementing a task-oriented conversational agent trained on annotated dialogues related to specific tasks. The agent’s per formance will be evaluated using metrics such as belief accuracy, belief loss, response accuracy, and response loss. The results have been analyzed to identify the strengths and weaknesses of the T5 transformer, the current state-of-the-art model in task-oriented dialogue generation . Experimental results demonstrate that MegaT outperforms the T5-based agent in terms of generating accurate, fluent, and coherent responses to user queries, as well as handling longer sequences of text and producing more informative and engag ing responses. We also found that our proposed Transient Global attention for task-oriented dialogue systems produce better results than the local at tention mechanism used in LongT5 on MultiWoz 2.2 dataset. The thesis aims to contribute to the development of more effective conversational agents by 1 leveraging the LongT5 model for generating high-quality task-oriented dia logues. This Study provides insights into the use of this recent transformer model and paves the way for further advancements in the field of dialogue generation with conversational agents. . Furthermore, it opens new avenues for future research in the field of dialogue generation with conversational agents.