DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation
The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease the number of required steps to reach a certain translation quality. The distilled model enjoys the computational benefits of early iterations while preserving the enhancements from several iterative steps. DiMS relies on two models namely student and teacher. The student is optimized to predict the output of the teacher after multiple decoding steps while the teacher follows the student via a slow-moving average. The moving average keeps the teacher's knowledge updated and enhances the quality of the labels provided by the teacher. During inference, the student is used for translation and no additional computation is added. We verify the effectiveness of DiMS on various models obtaining 7.8 and 12.9 BLEU points improvements in single-step translation accuracy on distilled and raw versions of WMT'14 De-En.
Code (1)
Tasks
de-enMachine TranslationTranslationSimilar Papers 제목 키워드 기반
S$^{2}$-DMs:Skip-Step Diffusion Models
Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inheren…
Denoising Diffusion Implicit Models
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate samp…
DenoisingImage GenerationGreedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a r…
Face Morphing Attack DetectionFace RecognitionGenerative Adversarial NetworkImage MorphingPseudo Numerical Methods for Diffusion Models on Manifolds
Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce final samples. Several prior works…
DenoisingImage GenerationIterative Neural Autoregressive Distribution Estimator NADE-k
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple s…
Density EstimationImage GenerationMissing ValuesVariational Inference