paper-with-me

홈 › Papers

DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text

2018-02-05 · Jingjing Xu, Xuancheng Ren, Junyang Lin, Xu sun

Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for "novel" and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines. The code is available at https://github.com/lancopku/DPGAN

📄 PDF Abstract BibTeX arXiv:1802.01345

Code (3)

lancopku/DPGAN 공식 구현 tf
AIJoris/DPAC-DialogueGAN pytorch
jsbaan/DPAC-DialogueGAN pytorch

Tasks

Dialogue GenerationDiversityGenerative Adversarial NetworkLanguage ModelingLanguage ModellingReview GenerationText Generation

Similar Papers 제목 키워드 기반

Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation

2018-10-01 · EMNLP 2018 10 · Jingjing Xu, Xuancheng Ren, Junyang Lin, Xu sun

Existing text generation methods tend to produce repeated and {''}boring{''} expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN)…

Dialogue GenerationDiversityGenerative Adversarial NetworkLanguage Modeling+5

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

2018-09-16 · NeurIPS 2018 12 · Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan 외

Responses generated by neural conversational models tend to lack informativeness and diversity. We present Adversarial Information Maximization (AIM), an adversarial learning strategy that addresses these two related but…

Conversational Response GenerationDiversityInformativeness

Can the Transformer Be Used as a Drop-in Replacement for RNNs in Text-Generating GANs?

2021-08-26 · RANLP 2021 9 · Kevin Blin, Andrei Kucharavy

In this paper we address the problem of fine-tuned text generation with a limited computational budget. For that, we use a well-performing text generative adversarial network (GAN) architecture - Diversity-Promoting GAN …

DiversityGenerative Adversarial NetworkText Generation

RelGAN: Relational Generative Adversarial Networks for Text Generation

2019-05-01 · ICLR 2019 5 · Weili Nie, Nina Narodytska, Ankit Patel

Generative adversarial networks (GANs) have achieved great success at generating realistic images. However, the text generation still remains a challenging task for modern GAN architectures. In this work, we propose RelG…

DiversityText Generation

Data InStance Prior (DISP) in Generative Adversarial Networks

2020-12-08 · Puneet Mangla, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy 외

Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availability of a large amount of training data…

Data AugmentationDiversityImage GenerationTransfer Learning+1