Adversarial Ranking for Language Generation

By Kevin Qinghong Lin, Dianqi Li, Xiaodong He, Ming-Ting Sun, Zhengyou Zhang. 2017

350 citations recorded by the source corpus.

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than training the discriminator to learn and assign absolute binary predicate for individual data sample, the proposed RankGAN is able to analyze and rank a collection of human-written and machine-written sentences by giving a reference group. By viewing a set of data samples collectively and evaluating their quality through relative ranking scores, the discriminator is able to make better assessment which in turn helps to learn a better generator. The proposed RankGAN is optimized through the policy gradient technique. Experimental results on multiple public datasets clearly demonstrate the effectiveness of the proposed approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Generative Models

Citations in the corpus

Automatic Detection of Generated Text is Easiest when Humans are Fooled (2019, background): “Finally, discriminators for whether text is machine-generated are a promising research direction in adversarial training (Lin et al., 2017; Li et al., 2017) and in”
ColdGANs: Taming Language GANs with Cautious Sampling Strategies (2020, methodology): “Following [7, 21, 39, 15, 5, 23], we used the EMNLP2017 news dataset.”
Towards Coherent and Cohesive Long-form Text Generation (2018, background): “, 2014) to incorporate feedback signals for text generation (Yu et al., 2017; Lin et al., 2017; Zhang et al., 2017; Guo et al., 2017; Fedus et al., 2018; Zhang et al., 2018).”
CausaLM: Causal Model Explanation Through Counterfactual Language Models (2020, background): “While in some cases, such as those presented in their paper, it might be plausible to generate counterfactual examples, in most cases in NLP it is still too hard to generate realistic texts with conditional generative models (Lin et al. 2017; Che et al. 2017; Rajeswar et al. 2017; Guo et al. 2018).”
Texygen: A Benchmarking Platform for Text Generation Models (2018, methodology): “Since then, many methods about improving Seq-GAN are proposed to further develop SeqGAN in many aspects; examples include gradient vanishing (MaliGAN [3], RankGAN [10], BRA in LeakGAN [5]), long-term robustness (LeakGAN).”
Recent Progress on Generative Adversarial Networks (GANs): A Survey (2019, background): “Lin et al. [62] proposed a RankGAN to generate sentences.”
Long Text Generation via Adversarial Training with Leaked Information (2017, methodology): “Since then, various methods have been proposed in text generation via GAN (Lin et al. 2017; Rajeswar et al. 2017; Che et al. 2017).”
Language GANs Falling Short (2018, background): “Notably, RankGAN (Lin et al., 2017), MaliGAN (Che et al., 2017), TextGAN (Zhang et al., 2017), LeakGAN (Guo et al., 2017) and IRL-GAN (Shi et al., 2018) were proposed soon after.”
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation (2019, neutral): “…related to the recent work on applying retrieval mechanisms to augment text generation, such as image captioning (Kuznetsova et al., 2013; Mason and Charniak, 2014), dialogue generation (Song et al., 2016; Yan et al., 2016; Wu et al., 2018) and style transfer (Lin et al., 2017; Li et al., 2018).”
TextGAIL: Generative Adversarial Imitation Learning for Text Generation (2020, methodology): “There are many other text GANs (Ke et al., 2019; Che et al., 2017; Guo et al., 2018; Lin et al., 2017; Nie et al., 2019) that tried to solve the stability problem.”
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “While GANs have received much attention in the overall deep learning literature [52, 53, 98, 121, 199], this has not been reflected in forecasting.”
Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework (2019, methodology): “Differently, our response generator is trained with target-speciﬁc skeletons.”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “Ranker GAN (Rank-GAN) [150] proposes a novel high-quality language (sentence) generation method by substituting the discriminator with a ranker network and achieved exceptional performances.”
Why I like it: multi-task learning for recommendation and explanation (2018, background): “These adversarially trained models have demonstrated superior performance to their maximum likelihood counterparts, particularly in the task of natural language generation [27].”
Open Event Extraction from Online Text using a Generative Adversarial Network (2019, methodology): “Based on the policy gradient, Lin et al. (2017) proposed RankGAN to capture the rich structures of language by ranking and analyzing a collection of human-written and machine-written sentences.”
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? (2019, methodology): “We believe the reason is that RankGAN still relies on MLE pre-training.”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, methodology): “We formulate a relevance score of the aggregate representation given a reference candidate by the cosine similarity [16]:”
Step-unrolled Denoising Autoencoders for Text Generation (2021, result): “, 2017), RankGAN (Lin et al., 2017), MaliGAN (Che et al.”
How Generative Adversarial Networks and Its Variants Work : An Overview of GAN (2017, methodology): “RankGAN [70] suggests language generation methods using text data generation and a ranker instead of a conventional discriminator.”
Survey on reinforcement learning for language processing (2021, methodology): “2017), RankGAN (Lin et al.”