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

TL;DR

This paper introduces a topic-aware chatbot model that combines RNNs with NMF-based topic attention, allowing for flexible topic switching and improved contextual responses in conversational AI.

Contribution

It presents a novel integration of NMF-derived topic vectors into RNN-based chatbots, enabling dynamic topic control and enhanced response relevance.

Findings

Outperforms non-topic RNN chatbots in response quality

Enables easy switching of topics via NMF vectors

Provides contextually relevant answers based on selected topics

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.