Papers › MaskGAN: Better Text Generation via Filling in the _______

MaskGAN: Better Text Generation via Filling in the _______

1 Jan 2018ICLR 2018 1archive 2025-07-28

William Fedus, Ian Goodfellow, Andrew M. Dai

Neural text generation models are often autoregressive language models or seq2seq models. Neural autoregressive and seq2seq models that generate text by sampling words sequentially, with each word conditioned on the previous model, are state-of-the-art for several machine translation and summarization benchmarks. These benchmarks are often defined by validation perplexity even though this is not a direct measure of sample quality. Language models are typically trained via maximum likelihood and most often with teacher forcing. Teacher forcing is well-suited to optimizing perplexity but can result in poor sample quality because generating text requires conditioning on sequences of words that were never observed at training time. We propose to improve sample quality using Generative Adversarial Network (GANs), which explicitly train the generator to produce high quality samples and have shown a lot of success in image generation. GANs were originally to designed to output differentiable values, so discrete language generation is challenging for them. We introduce an actor-critic conditional GAN that fills in missing text conditioned on the surrounding context. We show qualitatively and quantitatively, evidence that this produces more realistic text samples compared to a maximum likelihood trained model.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationMachine TranslationMultivariate Time Series ImputationText GenerationTranslation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multivariate Time Series Imputation PEMS-SF MaskGAN L2 Loss (10^-4) 6.02 #4 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionLSTMSeq2SeqSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections