2017 AHybridConvolutionalVariational

• (Semeniuta et al., 2017) ⇒ Stanislau Semeniuta, Aliaksei Severyn, and Erhardt Barth. (2017). “A Hybrid Convolutional Variational Autoencoder for Text Generation.” In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017). DOI:10.18653/v1/D17-1066.

Subject Headings: Natural Language Generation Task.

Notes

• Version(s) and Link(s):
  • ACL Anthology: https://www.aclweb.org/anthology/D17-1066/
  • ArXiv: https://arxiv.org/abs/1702.02390
  • DBLP: https://dblp.org/rec/html/conf/emnlp/SemeniutaSB17

Cited By

• Google Scholar: ~ 116 Citations.
• Semantic Scholar: ~ 115 Citations.
• MS Academic: ~ 99 Citations.

Quotes

Abstract

In this paper we explore the effect of architectural choices on learning a variational autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid the issue of the VAE collapsing to a deterministic model.

BibTeX

@inproceedings{2017_AHybridConvolutionalVariational,
  author    = {Stanislau Semeniuta and
               Aliaksei Severyn and
               Erhardt Barth},
  editor    = {Martha Palmer and
               Rebecca Hwa and
               Sebastian Riedel},
  title     = {A Hybrid Convolutional Variational Autoencoder for Text Generation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural
               Language Processing, {EMNLP} 2017, Copenhagen, Denmark, September
               9-11, 2017},
  pages     = {627--637},
  publisher = {Association for Computational Linguistics},
  year      = {2017},
  url       = {https://doi.org/10.18653/v1/d17-1066},
  doi       = {10.18653/v1/d17-1066},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2017 AHybridConvolutionalVariational	Aliaksei Severyn Stanislau Semeniuta Erhardt Barth			A Hybrid Convolutional Variational Autoencoder for Text Generation						2017