Generating Text via Adversarial Training

By Yizhe Zhang, Zhe Gan, Lawrence Carin. 2016

173 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Adversarial Feature Matching for Text Generation (2017, methodology): “Here we consider a soft-argmax operator (Zhang et al., 2016), i.”
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks (2017, methodology): “, 2016) or a soft-argmax function (Zhang et al., 2016) to approximate the gradient of the model from discrete samples.”
A Hybrid Convolutional Variational Autoencoder for Text Generation (2017, background): “GANs have proven to be very effective in the Computer Vision domain (Radford et al., 2015; Denton et al., 2015; Salimans et al., 2016) but so far have gained little traction in the NLP community (Yu et al., 2016; Zhang and Gan, 2016).”
Product Question Intent Detection using Indicative Clause Attention and Adversarial Learning (2018, unknown): “[31] applied adversarial learning for text generation.”
KDGAN: Knowledge Distillation with Generative Adversarial Networks (2018, background): “GAN has only recently been introduced to generate discrete data [16, 54, 55] because discrete data makes it difficult to pass gradients from a discriminator backward to update a generator.”
Controllable Text Generation (2017, background): “Very few recent attempts of using VAEs (Bowman et al., 2015; Tang et al., 2016) and GANs (Yu et al., 2017; Zhang et al., 2016) have been made to investigate generic text generation, while their generated text is largely randomized and uncontrollable.”
Time-series Generative Adversarial Networks (2019, background): “A multitude of applied studies have since utilized these frameworks to generate synthetic sequences in such diverse domains as text [15], finance [16], biosignals [17], sensor [18] and smart grid data [19], as well as renewable scenarios [20].”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “GANs have also been used in text generation [87], [383]– [385] and speech language processing [94].”
Generative adversarial networks: introduction and outlook (2017, background): “Zhang et al. [47] propose to generate realistic sentence with GANs, by using long short-term memory and convolutional neural networks for adversarial training.”
Language Generation with Recurrent Generative Adversarial Networks without Pre-training (2017, background): “Consequently, past work on using GANs for text generation has been based on pre-training (Yu et al., 2016; Li et al., 2017; Yang et al., 2017; Wu et al., 2017; Liang et al., 2017; Zhang et al., 2016; Shetty et al., 2017)”
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup (2020, background): “Prevailing generative models (Zhang et al., 2016; Bowman et al., 2016) are inapplicable because they can only generate word sequences without labels.”
Evolutionary Generative Adversarial Networks (2018, background): “Therefore, GANs have recently been successfully applied to image generation [2]–[6], image editing [7]–[10], video prediction [11]–[13], and many other tasks [14]–[18].”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, methodology): “In [121], this problem was solved by making the word prediction at every time “soft” at the word embedding space.”
Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks (2017, methodology): “, 2016) or a soft-argmax function (Zhang et al., 2016) to approximate the gradient of the model from discrete samples.”
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (2017, background): “Similarly, (Zhang et al., 2016) generate the text from random noise via adversarial training.”
On the Weaknesses of Reinforcement Learning for Neural Machine Translation (2019, background): “For some recent work on RL for NMT, see (Zhang et al., 2016; Li et al., 2017; Wu et al., 2017; Yu et al., 2017; Yang et al., 2018).”
Toward Controlled Generation of Text (2017, background): “Very few recent attempts of using VAEs (Bowman et al., 2015; Tang et al., 2016) and GANs (Yu et al., 2017; Zhang et al., 2016) have been made to investigate generic text generation, while their generated text is largely randomized and uncontrollable.”