Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated subsequence. MCTS is computationally intensive, but the performance of REGS is worse than MCTS. In this paper, we propose stepwise GAN (StepGAN), in which the discriminator is modified to automatically assign scores quantifying the goodness of each subsequence at every generation step. StepGAN has significantly less computational costs than MCTS. We demonstrate that StepGAN outperforms previous GAN-based methods on both synthetic experiment and chit-chat dialogue generation.
Code (1)
Tasks
Dialogue GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Time-series Transformer Generative Adversarial Networks
Many real-world tasks are plagued by limitations on data: in some instances very little data is available and in others, data is protected by privacy enforcing regulations (e.g. GDPR). We consider limitations posed speci…
Question AnsweringTime SeriesTime Series AnalysisTime Series GenerationSlimmable Generative Adversarial Networks
Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications. In particular, for…
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
This paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. The generator aims to g…
Machine TranslationNMTSentenceTranslationImproving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions. However, these models cannot be directly applied …
Generative Adversarial NetworkImage InpaintingTime-series Generation by Contrastive Imitation
Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepwise) transitions, but its open-loop roll…
Time SeriesTime Series Generation