2017 TowardControlledGenerationofTex

• (Hu et al., 2017) ⇒ Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. (2017). “Toward Controlled Generation of Text.” In: Proceedings of the 34th International Conference on Machine Learning, (ICML 2017), Sydney, NSW, Australia, 6-11 August 2017.

Subject Headings: Natural Language Processing, Text Generation Task.

Notes

• Pre-print(s) and Other Link(s):
  • PMLR: http://proceedings.mlr.press/v70/hu17e.html
  • ArXiv: https://arxiv.org/abs/1703.00955
  • DBLP: https://dblp.org/rec/html/conf/icml/HuYLSX17

Cited By

• Google Scholar: ~ 323 Citations.
• Semantic Scholar: ~ 340 Citations.
• MS Academic: ~ 280 Citations.

Quotes

Abstract

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible text sentences, whose attributes are controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders (VAEs) and holistic attribute discriminators for effective imposition of semantic structures. The model can alternatively be seen as enhancing VAEs with the wake-sleep algorithm for leveraging fake samples as extra training data. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns interpretable representations from even only word annotations, and produces short sentences with desired attributes of sentiment and tenses. Quantitative experiments using trained classifiers as evaluators validate the accuracy of sentence and attribute generation.

BibTeX

@inproceedings{2017_TowardControlledGenerationofTex,
  author    = {Zhiting Hu and
               Zichao Yang and
               Xiaodan Liang and
               Ruslan Salakhutdinov and
               Eric P. Xing},
  editor    = {Doina Precup and
               Yee Whye Teh},
  title     = {Toward Controlled Generation of Text},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning,
               (ICML 2017), Sydney, NSW, Australia, 6-11 August 2017},
  series    = {Proceedings of Machine Learning Research},
  volume    = {70},
  pages     = {1587--1596},
  publisher = {PMLR},
  year      = {2017},
  url       = {http://proceedings.mlr.press/v70/hu17e.html},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2017 TowardControlledGenerationofTex	Eric P. Xing Ruslan Salakhutdinov Zhiting Hu Zichao Yang Xiaodan Liang			Toward Controlled Generation of Text						2017