Pretraining

Image to Video Domain Adaptation Using Web Supervision WACV 2020 Implicit Discourse Relation Classification: We Need to Talk about Evaluation ACL 2020 Improving Event Duration Prediction via Time-aware Pre-training EMNLP 2020 Improving Transformer-Based Speech Recognition with Unsupervised Pre-Training and Multi-Task Semantic Knowledge Learning Interspeech 2020 Information-Theoretic Probing for Linguistic Structure ACL 2020 Infotec + CentroGEO at SemEval-2020 Task 8: Deep Learning and Text Categorization approach for Memes classification SemEval 2020 Injecting Numerical Reasoning Skills into Language Models ACL 2020 IRLab_DAIICT at SemEval-2020 Task 12: Machine Learning and Deep Learning Methods for Offensive Language Identification SemEval 2020 ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling SemEval 2020 Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation ACL 2020 KAFK at SemEval-2020 Task 12: Checkpoint Ensemble of Transformers for Hate Speech Classification SemEval 2020 KAFK at SemEval-2020 Task 8: Extracting Features from Pre-trained Neural Networks to Classify Internet Memes SemEval 2020 KDELAB at SemEval-2020 Task 12: A System for Estimating Aggression of Tweets Using Two Layers of BERT Features SemEval 2020 KFU NLP Team at SMM4H 2020 Tasks: Cross-lingual Transfer Learning with Pretrained Language Models for Drug Reactions COLING 2020 Knowledge Consistency between Neural Networks and Beyond ICLR 2020 Large Batch Optimization for Deep Learning: Training BERT in 76 minutes ICLR 2020 Large-Scale Adversarial Training for Vision-and-Language Representation Learning NeurIPS 2020 LAST at SemEval-2020 Task 10: Finding Tokens to Emphasise in Short Written Texts with Precomputed Embedding Models and LightGBM SemEval 2020 Learning and Evaluating Contextual Embedding of Source Code ICML 2020 Learning Efficient Task-Specific Meta-Embeddings with Word Prisms COLING 2020 Learning Emotion from 100 Observations: Unexpected Robustness of Deep Learning under Strong Data Limitations COLING 2020 LEARNING EXECUTION THROUGH NEURAL CODE FUSION ICLR 2020 Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually) EMNLP 2020 Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning WACV 2020 Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions Interspeech 2020