Self-Adversarial Learning with Comparative Discrimination for Text Generation
Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. In contrast to standard GANs that use a binary classifier as its discriminator to predict whether a sample is real or generated, SAL employs a comparative discriminator which is a pairwise classifier for comparing the text quality between a pair of samples. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. This self-improvement reward mechanism allows the model to receive credits more easily and avoid collapsing towards the limited number of real samples, which not only helps alleviate the reward sparsity issue but also reduces the risk of mode collapse. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity, and yields more stable performance compared to the previous GANs for text generation.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitySentenceText GenerationSimilar Papers 제목 키워드 기반
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation
Text generation with generative adversarial networks (GANs) can be divided into the text-based and code-based categories according to the type of signals used for discrimination. In this work, we introduce a novel text-b…
Text GenerationMGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance. Existing methods for text-to-bird/flower synthesis are still far fr…
DiversityGenerative Adversarial NetworkImage GenerationSelf-Generative Adversarial Fine-Tuning for Large Language Models
Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent s…
Reinforcement LearningAdversarial Text Generation via Sequence Contrast Discrimination
In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference. Specifically, our discriminator contains a…
Adversarial TextText GenerationFairGAN: Fairness-aware Generative Adversarial Networks
Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on…
FairnessGeneral Classification