An AI Design of Robot Communication using Natural Language Processing (NLP)

No Thumbnail Available
Islam, Saiful
Issue Date
MSc in Artificial Intelligence
Dublin Business School
This study presents a novel approach to robot communication through the lens of Natural Language Processing (NLP), leveraging the capabilities of the BartForConditionalGeneration model from Hugging Face's transformers. The research's core objective is to engineer an AI framework, designated as 'nqa_dbs_model' (Natural Question-Answer Dublin Business School Model), that excels in interpreting and responding to queries using diverse datasets. The model's training involved a dual dataset strategy: firstly, a General Knowledge dataset sourced from Google's Natural Questions, and secondly, a bespoke dataset focused on Dublin Business School (DBS), compiled through meticulous web scraping. In assessing the model's efficacy, a comparative analysis was conducted against OpenAI's gpt-3.5-turbo model. The outcomes reveal a notable proficiency of the 'nqa_dbs_model' in addressing specific organizational queries related to DBS, a feature not mirrored in the gpt-3.5-turbo model. This distinction highlights the 'nqa_dbs_model’s' advanced capability in generating context-specific responses, thereby enhancing the scope of AI in targeted communication scenarios. The conclusion drawn from this research underscores the importance of specialized dataset training in elevating the potential of AI models within the realm of robotic communication, offering a pathway to more nuanced and contextually relevant interactions in AI-assisted environments.