Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems

by   Bo-Hsiang Tseng, et al.
University of Cambridge

Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent information at the sentence level during generation using the conditional variational autoencoder architecture. We demonstrate that our model outperforms the original RNN-based generator, while yielding highly diverse sentences. In addition, our model performs better when the training data is limited.


page 1

page 2

page 3

page 4


Semantic Refinement GRU-based Neural Language Generation for Spoken Dialogue Systems

Natural language generation (NLG) plays a critical role in spoken dialog...

Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks

Natural language generation (NLG) is a critical component in a spoken di...

MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System

We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controlla...

Discriminative and Generative Transformer-based Models For Situation Entity Classification

We re-examine the situation entity (SE) classification task with varying...

Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking

The natural language generation (NLG) component of a spoken dialogue sys...

Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems

Scarcity of training data for task-oriented dialogue systems is a well k...

Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

Natural language generation (NLG) is a critical component of spoken dial...

Code Repositories


Semantically Conditioned Variational Autoencoder for NLG

view repo

Please sign up or login with your details

Forgot password? Click here to reset