{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"1909.13788","title":"Revisiting Self-Training for Neural Sequence Generation","created":"2019-09-30","cited_by_count":155},{"id":"1512.08571","title":"Structured Pruning of Deep Convolutional Neural Networks","created":"2015-12-29","cited_by_count":149},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"1703.02573","title":"Data Noising as Smoothing in Neural Network Language Models","created":"2017-03-07","cited_by_count":78},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"1611.06321","title":"Learning the Number of Neurons in Deep Networks","created":"2016-11-19","cited_by_count":69},{"id":"1509.07577","title":"A Review of Feature Selection Methods Based on Mutual Information","created":"2015-09-24","cited_by_count":67},{"id":"2106.16038","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","created":"2021-06-30","cited_by_count":65},{"id":"2105.13022","title":"Adaptive Nearest Neighbor Machine Translation","created":"2021-05-27","cited_by_count":58},{"id":"1606.09274","title":"Compression of Neural Machine Translation Models via Pruning","created":"2016-06-29","cited_by_count":44},{"id":"1905.13678","title":"Learning Sparse Networks Using Targeted Dropout","created":"2019-05-31","cited_by_count":40},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37},{"id":"1905.04748","title":"Approximated Oracle Filter Pruning for Destructive CNN Width Optimization","created":"2019-05-12","cited_by_count":35},{"id":"1909.12486","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","created":"2019-09-27","cited_by_count":29},{"id":"2002.03067","title":"Description Based Text Classification with Reinforcement Learning","created":"2020-02-08","cited_by_count":27},{"id":"1907.07384","title":"Feature Selection via Mutual Information: New Theoretical Insights","created":"2019-07-17","cited_by_count":17},{"id":"1910.06360","title":"Structured Pruning of a BERT-based Question Answering Model","created":"2019-10-14","cited_by_count":16},{"id":"2003.09833","title":"SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection","created":"2020-03-22","cited_by_count":13},{"id":"2011.08626","title":"Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining","created":"2020-11-17","cited_by_count":5}],"next_cursor":null}