Self-Adversarial Learning with Comparative Discrimination for Text Generation

By Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou. 2020

20 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

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

Citations in the corpus

ColdGANs: Taming Language GANs with Cautious Sampling Strategies (2020, background): “…provided by the discriminator (see Section 3.2), a large body of works focused on deﬁning denser rewards: ranking and comparative discriminators [20, 59], sequential discriminators where the rewards are provided at each time step of the generation [39, 23], or using masked language modeling [11].”
Discriminative Adversarial Search for Abstractive Summarization (2020, background): “However, due to reward sparsity and mode collapse (Zhou et al., 2020), text GANs failed so far to be competitive with state-of-the-art models trained with teacher forcing on NLG tasks (Caccia et al., 2018; Clark et al., 2019), and are mostly evaluated on synthetic datasets.”
TextGAIL: Generative Adversarial Imitation Learning for Text Generation (2020, background): “algorithm, to train the generator with a reward deﬁned by the discriminator’s prediction on the generated sample. However, it suffers from a high variance of gradients. There are many other text GANs [10, 4, 6, 13, 16, 33]. However, as Caccia et al. [3] has shown, many of them are worse than their M”