Adversarial Generation of Natural Language

Rajeswar, Sai; Subramanian, Sandeep; Dutil, Francis; Pal, Christopher; Courville, Aaron

doi:10.48550/arxiv.1705.10929

Cited by 60 publications

(57 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such a framework, the generator is not directly exposed to the ground truth data, but instead learns to imitate it using global feedback from the discriminator. This has led to several attempts to use GANs for text generation, with a generator using either a recurrent neural network (RNN) Guo et al, 2017;Press et al, 2017;Rajeswar et al, 2017), or a Convolutional Neural Network (CNN) (Gulrajani et al, 2017;Rajeswar et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Evaluating Text GANs as Language Models

Tevet,

Habib,

Shwartz

et al. 2018

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of "exposure bias". However, A major hurdle for understanding the potential of GANs for text generation is the lack of a clear evaluation metric. In this work, we propose to approximate the distribution of text generated by a GAN, which permits evaluating them with traditional probability-based LM metrics. We apply our approximation procedure on several GAN-based models and show that they currently perform substantially worse than stateof-the-art LMs. Our evaluation procedure promotes better understanding of the relation between GANs and LMs, and can accelerate progress in GAN-based text generation.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating Text GANs as Language Models

Tevet,

Habib,

Shwartz

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Over the years, GAN [54] has been used in many computer vision related tasks [55]- [57] as well as in the natural language domain [58], [59]. Furthermore, GAN has also been used for reconstructing medical images [60]- [62], face images [63] etc.…”

Section: B Applications Of Ganmentioning

confidence: 99%

SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network

Karim,

Rahnavard

2021

Preprint

View full text Add to dashboard Cite

Single-pixel imaging is a novel imaging scheme that has gained popularity due to its huge computational gain and potential for a low-cost alternative to imaging beyond the visible spectrum. The traditional reconstruction methods struggle to produce a clear recovery when one limits the number of illumination patterns from a spatial light modulator. As a remedy, several deep-learning-based solutions have been proposed which lack good generalization ability due to the architectural setup and loss functions. In this paper, we propose a generative adversarial network based reconstruction framework for singlepixel imaging, referred to as SPI-GAN. Our method can reconstruct images with 17.92 dB PSNR and 0.487 SSIM, even if the sampling ratio drops to 5%. This facilitates much faster reconstruction making our method suitable for single-pixel video. Furthermore, our ResNet-like architecture for generator leads to useful representation learning that allows us to reconstruct completely unseen objects. The experimental results demonstrate that SPI-GAN achieves significant performance gain, e.g. near 3dB PSNR gain, over the current state-of-the-art method.

show abstract

“…They were among the first to apply such techniques to neural language generation, but to date, training with log-likelihood maximization (Xie, 2017) has been the main working horse. Alternatively, Rajeswar et al (2017) and have tried using Generative Adversarial Neural Networks (GANs) for text generation. However, Caccia et al (2018) observed problems with training GANs and show that to date, they are unable to beat canonical sequence decoder methods.…”

Section: Language Generationmentioning

confidence: 99%

Clinically Accurate Chest X-Ray Report Generation

Liu,

Hsu,

McDermott

et al. 2019

Preprint

View full text Add to dashboard Cite

The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMIC-CXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.

show abstract

Adversarial Generation of Natural Language

Cited by 60 publications

References 13 publications

Evaluating Text GANs as Language Models

Evaluating Text GANs as Language Models

SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network

Clinically Accurate Chest X-Ray Report Generation

Contact Info

Product

Resources

About