LSTM based Ensemble Network to enhance the learning of Long-term Dependencies in Chatbot

Abstract

A chatbot is a software that can reproduce a discussion portraying a specific dimension of articulation among people and machines utilizing Natural Human Language. With the advent of AI, chatbots have developed from being minor guideline based models to progressively modern models. A striking highlight of the current chatbot frameworks is their capacity to maintain and support explicit highlights and settings of the discussions empowering them to have a human contact through the span of involvement. The paper expects to build up a detailed database with respect to the models utilized to deal with the learning of long haul conditions in a chatbot. The paper proposes a crossbreed Long Short Term Memory based Ensemble Network arrangement model to save the continuation of the specific situation. The proposed model uses a characterized number of Long Short Term Memory Networks as a major aspect of the amassed model working as one to create the aggregate forecast class for the info inquiry handled.