Data Augmentation

Few-Shot Pill Recognition CVPR 2020 Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness EMNLP 2020 Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory EMNLP 2020 FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence NeurIPS 2020 Gaming Corpus for Studying Social Screams Interspeech 2020 GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing Data CVPR 2020 GAN-Based Data Generation for Speech Emotion Recognition Interspeech 2020 GenAug: Data Augmentation for Finetuning Text Generators EMNLP 2020 Generating Diverse Translation by Manipulating Multi-Head Attention AAAI 2020 Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations EMNLP 2020 Generative Data Augmentation for Commonsense Reasoning EMNLP 2020 Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data ICML 2020 Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search NeurIPS 2020 Good-Enough Compositional Data Augmentation ACL 2020 GRACE: Generating Summary Reports Automatically for Cognitive Assistance in Emergency Response AAAI 2020 GradAug: A New Regularization Method for Deep Neural Networks NeurIPS 2020 Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency ACL 2020 Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis AACL 2020 Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation UAI 2020 Guiding Program Synthesis by Learning to Generate Examples ICLR 2020 Hard Negative Mixing for Contrastive Learning NeurIPS 2020 HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection COLING 2020 Heavy-tailed Representations, Text Polarity Classification & Data Augmentation NeurIPS 2020 High-contrast “gaudy” images improve the training of deep neural network models of visual cortex NeurIPS 2020 How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers? EMNLP 2020