Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization

After learning topic vectors from an auxiliary text corpus via NMF, the decoder is trained so that it is more likely to sample response words from the most correlated topic vectors. One of the main advantages in our architecture is that the user can easily switch the NMF-learned topic vectors so that the chatbot obtains desired topic-awareness. We demonstrate our model by training on a single conversational data set which is then augmented with topic matrices learned from different auxiliary data sets. We show that our topic-aware chatbot not only outperforms the non-topic counterpart, but also that each topic-aware model qualitatively and contextually gives the most relevant answer depending on the topic of question. Another area where deep learning algorithms have been successfully applied is sequence learning, which aims at understanding the structure of sequential data such as language, musical notes, and videos. One example of an application of deep learning in language modeling is conversational chatbots . A chatbot is a program that conducts a conversation with a user by simulating one side of it. Chatbots receive inputs from a user one message, or question, at a time, and then form a response that is sent back to the user. One of the most widely used machine learning techniques for sequence learning is Recurrent Neural Networks (RNN).