Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
This work addresses the need for more contextually relevant chatbots in conversational AI, though it is incremental as it builds on existing RNN and NMF methods.
The authors tackled the problem of creating a topic-aware chatbot by combining a Recurrent Neural Network encoder-decoder with a topic attention layer based on Nonnegative Matrix Factorization, resulting in a model that outperforms non-topic counterparts and provides contextually relevant answers based on question topics.
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.