Incorporating Discriminator in Sentence Generation: A Gibbs Sampling Method

Jinyue Su, Jiacheng Xu, Xipeng Qiu, Xuanjing Huang

AAAI 2018 pp. 5496-5503

doi:10.1609/AAAI.V32I1.11990 /aaai/2018/su2018aaai-incorporating/

Abstract

Generating plausible and fluent sentence with desired properties has long been a challenge. Most of the recent works use recurrent neural networks (RNNs) and their variants to predict following words given previous sequence and target label. In this paper, we propose a novel framework to generate constrained sentences via Gibbs Sampling. The candidate sentences are revised and updated iteratively, with sampled new words replacing old ones. Our experiments show the effectiveness of the proposed method to generate plausible and diverse sentences.

PDF AAAI Semantic Scholar

Cite

Text

Su et al. "Incorporating Discriminator in Sentence Generation: A Gibbs Sampling Method." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11990

Markdown

[Su et al. "Incorporating Discriminator in Sentence Generation: A Gibbs Sampling Method." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/su2018aaai-incorporating/) doi:10.1609/AAAI.V32I1.11990

BibTeX

@inproceedings{su2018aaai-incorporating,
  title     = {{Incorporating Discriminator in Sentence Generation: A Gibbs Sampling Method}},
  author    = {Su, Jinyue and Xu, Jiacheng and Qiu, Xipeng and Huang, Xuanjing},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {5496-5503},
  doi       = {10.1609/AAAI.V32I1.11990},
  url       = {https://mlanthology.org/aaai/2018/su2018aaai-incorporating/}
}