Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems. (arXiv:1812.08879v1 [cs.CL])

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.

Source link

Back to top button