Towards Text Generation with Adversarially Learned Neural Outlines

By Sandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron C. Courville, C. Pal. 2018

52 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.

1. Chunyuan Li
2. Jianfeng Gao
3. Zhe Gan
4. Yoshua Bengio
5. Minlie Huang
6. Mohit Bansal
7. Lawrence Carin
8. Yizhe Zhang

Citations in the corpus

• Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, background): “the produced latent space of an autoencoder [38].”
• On the Evaluation of Conditional GANs (2019, background): “Among the most promising approaches, Variational Auto-Encoders (VAEs) [20], auto-regressive models [43, 42] and Generative Adversarial Networks (GANs) [9] have been driving significant progress, with the latter at the forefront of a wide-range of applications [24, 52, 32, 46, 1, 38, 34].”
• Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020, background): “(3) NN-Outlines (Subramanian et al., 2018) proposes the use of a general purpose encoder for text generation, and we implement it using BERT.”
• Complementary Auxiliary Classifiers for Label-Conditional Text Generation (2020, methodology): “Baselines We compare with three baselines: (1) Ctrl-Gen (Hu et al. 2017); (2) ARAE (Zhao et al. 2017), and a version without using separate generatorsARAE-); and (3) NN-Outlines (Subramanian et al. 2018) proposes the use of a general purpose encoder for text generation, and we implement it using BER”
• Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators (2022, background): “…the ablation studies of ELECTRA (Clark et al., 2020), or directly operating in the hidden states of the generator instead of in its discrete output space which has been studied in adversarial learning based text generation research (Subramanian et al., 2018; Zhang et al., 2017; Zhao et al., 2018).”
• Artificial intelligence in the creative industries: a review (2020, methodology): “A conditioned GAN with an RNN architecture has been proposed for language translation in [25].”