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

arXiv1912.00315MaRDI QIDQ6330180

Author name not available (Why is that?)

Publication date: 30 November 2019

Abstract: We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF). 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.

Has companion code repository: https://github.com/HanbaekLyu/RNN_NMF_chatbot

This page was built for publication: Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6330180)