Architectures

What Was Your Name Again? Interrogating Generative Conversational Models For Factual Consistency Evaluation EMNLP 2022 What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation ACL 2022 When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NeurIPS 2022 When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it NAACL 2022 When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks EMNLP 2022 When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer NAACL 2022 When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism AAAI 2022 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations ICLR 2022 When, where, and how to add new neurons to ANNs AutoML 2022 Where Does Linguistic Information Emerge in Neural Language Models? Measuring Gains and Contributions across Layers COLING 2022 Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NeurIPS 2022 Where to Pay Attention in Sparse Training for Feature Selection? NeurIPS 2022 Which side are you on? Insider-Outsider classification in conspiracy-theoretic social media ACL 2022 Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production EMNLP 2022 Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis CVPR 2022 Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power NeurIPS 2022 Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling ICML 2022 Wide Neural Networks Forget Less Catastrophically ICML 2022 Width & Depth Pruning for Vision Transformers AAAI 2022 Width is Less Important than Depth in ReLU Neural Networks COLT 2022 WikiHan: A New Comparative Dataset for Chinese Languages COLING 2022 Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models ICLR 2022 WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language ACL 2022 Wolfies at SemEval-2022 Task 8: Feature extraction pipeline with transformers for Multi-lingual news article similarity SemEval 2022 Word-level Morpheme segmentation using Transformer neural network NAACL 2022