Controllable Text Generation

By Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, Eric P. Xing. 2017

114 citations recorded by the source corpus.

Subfields: Natural Language Processing, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Generative Models

Citations in the corpus

Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019, background): “Shen et al. (2017); Hu et al. (2017) train variational auto-encoders for style transfer that rely on learning disentangled latent representations for style and content.”
Unsupervised Machine Translation Using Monolingual Corpora Only (2017, background): “Before that, Hu et al. (2017) trained a variational autoencoder (VAE) where the decoder input is the concatenation of an unstructured latent vector, and a structured code representing the attribute of the sentence to generate.”
Learning to Generate Reviews and Discovering Sentiment (2017, methodology): “Hu et al. (2017) and Dong et al. (2017) both designed conditional generative models to disentangle the content of text from various attributes like sentiment or tense.”
Controlling Linguistic Style Aspects in Neural Language Generation (2017, methodology): “The work of Hu et al. (2017) features a VAE based method coupled with a discriminator network that tackles the same problem as ours: conditioning on multiple aspects of the generated text.”
Style Transfer from Non-Parallel Text by Cross-Alignment (2017, methodology): “Our work most closely relates to approaches that do not utilize parallel data, but instead guide sentence generation from an indirect training signal (Mueller et al., 2017; Hu et al., 2017).”
Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “(Hu et al., 2017) proposed generating sentences whose attributes are controlled by learning disentangled latent representations with designated semantics.”
Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data (2017, background): “In addition, β -VAEs [14] are trained on the same data as the FHVAE to serve as the baseline feature extractor, from which we extract the latent variables z as the ASR feature and show the result in the third to the sixth rows.”
A Neural Representation of Sketch Drawings (2017, methodology): “This type of approach has been tested on VAE-GAN [21] hybrids on pixel images, and has recently been tested on text generation [12].”
Long Text Generation via Adversarial Training with Leaked Information (2017, background): “Generating text that mimics human’s expression has been studied for poem generation (Zhang and Lapata 2014), image captioning (Vinyals et al. 2015), dialogue system (Li et al. 2017) machine translation (Yang et al. 2017).”
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management (2017, background): “…the dialogue history, a dialogue policy (Young et al., 2013; Gaˇsi´c and Young, 2014; Budzianowski et al., 2017) to determine the dialogue ﬂow, and a natural language generator (Rieser and Lemon, 2009; Wen et al., 2015; Hu et al., 2017) to convert conceptual representations into system responses.”
Adversarial Generation of Natural Language (2017, background): “Recent work (Hu et al., 2017) generates sentences conditioned on certain attributes of language such as sentiment using a variational au-toencoders (VAEs) (Kingma and Welling, 2013) and holistic attribute discriminators.”
An Introduction to Variational Autoencoders (2019, background): “Another prominent application of VAEs is modeling of text and or sequential data (Bayer and Osendorfer, 2014; Bowman et al., 2015; Serban et al., 2017; Johnson et al., 2016; Karl et al., 2017; Fraccaro et al., 2016; Miao et al., 2016; Semeniuta et al., 2017; Zhao et al., 2017; Yang et al., 2017; Hu ”
Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning (2017, methodology): “In this work, we propose hierarchical nonparametric variational autoencoders, which combines treestructured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation space.”
Z-Forcing: Training Stochastic Recurrent Networks (2017, methodology): “In future work, it would be interesting to use a multitask learning setting, e.g. sentiment analysis as in (Hu et al., 2017).”
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models (2022, methodology): “After that, there is a surge of methods based on deep generative models, such as Variational Autoencoders (VAEs) [48, 125, 138, 142, 149, 154], Generative Adversarial Networks (GANs) [117, 140], and Energy-based Models [8, 25, 135, 166].”
Recurrent Topic-Transition GAN for Visual Paragraph Generation (2017, background): “The discrete nature of text samples hinders gradient back-propagation from the discriminators to the generator [9].”
3D Object Dense Reconstruction from a Single Depth View (2018, background): “Recently, deep generative models achieve impressive success in modeling complex high-dimensional data distributions, among which Generative Adversarial Networks (GANs) [12] and Variational Autoencoders (VAEs) [13] emerge as two powerful frameworks for generative learning, including image and text ge”