Abstract: In this work we explore a deep learning and natural language processing (NLP) based dialog system that generates responses from a conversation design perspective. We trained a feed forward neural net model on a carefully curated dataset of normal query-based questions related to Ecommerce. We show that end-to-end systems learn patterns very quickly from small datasets and thus, are able to transfer simple linguistic structures representing abstract concepts. We also integrated this chatbot in a simple web application, where users can directly interact with our chatbot. As we are using NLP our chatbot model is getting familiar to user’s responses and training itself to respond with better responses.
Keywords: Chatbot, AI Chatbot, Natural Language Processing, Deep Learning.
|
DOI:
10.17148/IJARCCE.2022.11306
