Pretraining

DELTA: DEEP LEARNING TRANSFER USING FEATURE MAP WITH ATTENTION FOR CONVOLUTIONAL NETWORKS ICLR 2019 Denoising based Sequence-to-Sequence Pre-training for Text Generation EMNLP 2019 Designing a Symbolic Intermediate Representation for Neural Surface Realization NAACL 2019 Effective Use of Transformer Networks for Entity Tracking EMNLP 2019 Efficient Training of BERT by Progressively Stacking ICML 2019 Embedding Time Expressions for Deep Temporal Ordering Models ACL 2019 End-to-End Learning of Representations for Asynchronous Event-Based Data ICCV 2019 Energy and Policy Considerations for Deep Learning in NLP ACL 2019 Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension ACL 2019 ERNIE: Enhanced Language Representation with Informative Entities ACL 2019 Estimating Information Flow in Deep Neural Networks ICML 2019 Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations EMNLP 2019 Explicit Cross-lingual Pre-training for Unsupervised Machine Translation EMNLP 2019 Extractive NarrativeQA with Heuristic Pre-Training EMNLP 2019 Fast AutoAugment NeurIPS 2019 Fusion Techniques for Utterance-Level Emotion Recognition Combining Speech and Transcripts Interspeech 2019 Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening ACML 2019 Graph HyperNetworks for Neural Architecture Search ICLR 2019 Graph Policy Gradients for Large Scale Robot Control CoRL 2019 Harnessing Pre-Trained Neural Networks with Rules for Formality Style Transfer EMNLP 2019 HHU at SemEval-2019 Task 6: Context Does Matter - Tackling Offensive Language Identification and Categorization with ELMo SemEval 2019 HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization ACL 2019 How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection NAACL 2019 Image Generation From Small Datasets via Batch Statistics Adaptation ICCV 2019 ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness ICLR 2019