Deep Learning

BERT-of-Theseus: Compressing BERT by Progressive Module Replacing EMNLP 2020 BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance ACL 2020 BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance EMNLP 2020 Bert Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets COLING 2020 BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining EMNLP 2020 Best Frame Selection in a Short Video WACV 2020 Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data COLING 2020 Best Practices for Scientific Research on Neural Architecture Search JMLR 2020 Better AMR-To-Text Generation with Graph Structure Reconstruction IJCAI 2020 Better Captioning With Sequence-Level Exploration CVPR 2020 Better Highlighting: Creating Sub-Sentence Summary Highlights EMNLP 2020 Better Set Representations For Relational Reasoning NeurIPS 2020 Better Sign Language Translation with STMC-Transformer COLING 2020 Beyond Accuracy: Behavioral Testing of NLP Models with CheckList ACL 2020 Beyond Classification: Whole Slide Tissue Histopathology Analysis By End-To-End Part Learning MIDL 2020 Beyond [CLS] through Ranking by Generation EMNLP 2020 Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks AAAI 2020 Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness AISTATS 2020 Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs NeurIPS 2020 Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube EMNLP 2020 Beyond Language: Learning Commonsense from Images for Reasoning EMNLP 2020 Beyond Network Pruning: a Joint Search-and-Training Approach IJCAI 2020 Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context CVPR 2020 Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? ICML 2020 Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels ICML 2020