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

12/01/2019
by   Yuchen Guo, et al.
16

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/28/2023

Neural Nonnegative Matrix Factorization for Hierarchical Multilayer Topic Modeling

We introduce a new method based on nonnegative matrix factorization, Neu...
research
12/07/2020

Nonnegative Matrix Factorization with Zellner Penalty

Nonnegative matrix factorization (NMF) is a relatively new unsupervised ...
research
10/22/2020

On a Guided Nonnegative Matrix Factorization

Fully unsupervised topic models have found fantastic success in document...
research
09/30/2021

A Generalized Hierarchical Nonnegative Tensor Decomposition

Nonnegative matrix factorization (NMF) has found many applications inclu...
research
03/03/2018

Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications

Nonnegative matrix factorization (NMF) has become a workhorse for signal...
research
01/02/2020

On Large-Scale Dynamic Topic Modeling with Nonnegative CP Tensor Decomposition

There is currently an unprecedented demand for large-scale temporal data...
research
09/21/2017

Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding

In this paper, we propose a novel recurrent neural network architecture ...

Please sign up or login with your details

Forgot password? Click here to reset