DE eng

Search in the Catalogues and Directories

Hits 1 – 2 of 2

1
A dual-attention hierarchical recurrent neural network for dialogue act classification
Li, R.; Lin, C.; Collinson, M.. - : Association for Computational Linguistics (ACL), 2019
BASE
Show details
2
A stable variational autoencoder for text modelling
Li, R.; Li, X.; Lin, C.; Collinson, M.; Mao, R.. - : Association for Computational Linguistics (ACL), 2019
Abstract: Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL term vanishing), where the posterior collapses to the prior and the model will ignore the latent codes in generative tasks. Such an issue is particularly prevalent when employing VAE-RNN architectures for text modelling (Bowman et al., 2016; Yang et al., 2017). In this paper, we present a new architecture called Full-Sampling-VAE-RNN, which can effectively avoid latent variable collapse. Compared to the general VAE-RNN architectures, we show that our model can achieve much more stable training process and can generate text with significantly better quality.
URL: http://eprints.whiterose.ac.uk/161488/1/W19-8673.pdf
http://eprints.whiterose.ac.uk/161488/
https://www.aclweb.org/anthology/W19-8673
BASE
Hide details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
2
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern