| DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment | Oct 19, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Automatic Learning of Subword Dependent Model Scales | Oct 18, 2021 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| NormFormer: Improved Transformer Pretraining with Extra Normalization | Oct 18, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization | Oct 18, 2021 | BIG-bench Machine Learningimage-classification | CodeCode Available | 1 |
| Reminding the Incremental Language Model via Data-Free Self-Distillation | Oct 17, 2021 | Data AugmentationLanguage Modeling | —Unverified | 0 |
| GNN-LM: Language Modeling based on Global Contexts via GNN | Oct 17, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| A Novel Metric for Evaluating Semantics Preservation | Oct 16, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Echo-Attention: Attend Once and Get N Attentions for Free | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| DEMix Layers: Disentangling Domains for Modular Language Modeling | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking | Oct 16, 2021 | Dialogue State TrackingLanguage Modeling | —Unverified | 0 |
| xGQA: Cross-Lingual Visual Question Answering | Oct 16, 2021 | Cross-Lingual TransferLanguage Modeling | —Unverified | 0 |
| On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation | Oct 16, 2021 | Domain AdaptationDomain Generalization | —Unverified | 0 |
| Prix-LM: Pretraining for Multilingual Knowledge Base Construction | Oct 16, 2021 | Bilingual Lexicon InductionCausal Language Modeling | CodeCode Available | 0 |
| Sharpness-Aware Minimization Improves Language Model Generalization | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages | Oct 16, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Improving Transformers with Probabilistic Attention Keys | Oct 16, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models | Oct 16, 2021 | counterfactualData Augmentation | CodeCode Available | 1 |
| HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression | Oct 16, 2021 | Few-Shot LearningKnowledge Distillation | CodeCode Available | 0 |
| ASR4REAL: An extended benchmark for speech models | Oct 16, 2021 | DiversityLanguage Modeling | —Unverified | 0 |
| A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models | Oct 16, 2021 | Image CaptioningLanguage Modeling | CodeCode Available | 1 |
| Invariant Language Modeling | Oct 16, 2021 | Domain GeneralizationLanguage Modeling | CodeCode Available | 1 |
| Hydra: A System for Large Multi-Model Deep Learning | Oct 16, 2021 | Deep LearningGPU | CodeCode Available | 1 |
| Leveraging Knowledge in Multilingual Commonsense Reasoning | Oct 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
