{"list":"other","total":55,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1611.04558","title":"Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation","created":"2016-11-14","cited_by_count":469},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1802.06893","title":"Learning Word Vectors for 157 Languages","created":"2018-02-19","cited_by_count":280},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2004.11867","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","created":"2020-04-24","cited_by_count":277},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"1903.00089","title":"Massively Multilingual Neural Machine Translation","created":"2019-02-28","cited_by_count":246},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"1911.07013","title":"Understanding and Improving Layer Normalization","created":"2019-11-16","cited_by_count":217},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"2001.09239","title":"Multi-task self-supervised learning for Robust Speech Recognition","created":"2020-01-25","cited_by_count":130},{"id":"1804.06323","title":"When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?","created":"2018-04-17","cited_by_count":126},{"id":"1511.06114","title":"Multi-task Sequence to Sequence Learning","created":"2015-11-19","cited_by_count":94},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"2004.06748","title":"Balancing Training for Multilingual Neural Machine Translation","created":"2020-04-14","cited_by_count":72},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"1901.09491","title":"Stiffness: A New Perspective on Generalization in Neural Networks","created":"2019-01-28","cited_by_count":46},{"id":"1906.07774","title":"On the interplay between noise and curvature and its effect on optimization and generalization","created":"2019-06-18","cited_by_count":44},{"id":"2001.07384","title":"Understanding Why Neural Networks Generalize Well Through GSNR of Parameters","created":"2020-01-21","cited_by_count":40},{"id":"1809.00252","title":"Parameter Sharing Methods for Multilingual Self-Attentional Translation Models","created":"2018-09-01","cited_by_count":33},{"id":"1909.06434","title":"Adaptive Scheduling for Multi-Task Learning","created":"2019-09-13","cited_by_count":24},{"id":"2009.13102","title":"Deep Transformers with Latent Depth","created":"2020-09-28","cited_by_count":17}],"next_cursor":null}