Question Answering based University Chatbot using Sequence to Sequence Model
Naing Naing Khin, Khin Mar Soe
Abstract
Educational chatbots have great potential to help students, teachers and education staff. They provide useful information in educational sectors for inquirers. Neural chatbots are more scalable and popular than earlier ruled-based chatbots. Recurrent Neural Network based Sequence to Sequence (Seq2Seq) model can be used to create chatbots. Seq2Seq is adapted for good conversational model for sequences especially in question answering systems. In this paper, we explore the ways of communication through neural network chatbot by using the Sequence to Sequence model with Attention Mechanism based on RNN encoder decoder model. This chatbot is intended to be used in university education sector for frequently asked questions about the university and its related information. It is the first Myanmar Language University Chatbot using neural network model and gets 0.41 BLEU score.