{"list":"other","total":73,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2004.13922","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","created":"2020-04-29","cited_by_count":266},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"1811.05701","title":"Plan-And-Write: Towards Better Automatic Storytelling","created":"2018-11-14","cited_by_count":234},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"1807.02478","title":"CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction","created":"2018-07-04","cited_by_count":170},{"id":"1811.02084","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","created":"2018-11-05","cited_by_count":169},{"id":"2006.09503","title":"Memory-Efficient Pipeline-Parallel DNN Training","created":"2020-06-16","cited_by_count":134},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"1810.07366","title":"A Span-Extraction Dataset for Chinese Machine Reading Comprehension","created":"2018-10-17","cited_by_count":84},{"id":"1904.09679","title":"Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension","created":"2019-04-21","cited_by_count":81},{"id":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"2102.07988","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","created":"2021-02-16","cited_by_count":75},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68},{"id":"1906.01265","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","created":"2019-06-04","cited_by_count":65},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61},{"id":"1806.00920","title":"DRCD: a Chinese Machine Reading Comprehension Dataset","created":"2018-06-04","cited_by_count":57},{"id":"2005.05635","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","created":"2020-05-12","cited_by_count":54},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52},{"id":"2005.00613","title":"A Controllable Model of Grounded Response Generation","created":"2020-05-01","cited_by_count":49},{"id":"2006.03535","title":"CoCon: A Self-Supervised Approach for Controlled Text Generation","created":"2020-06-05","cited_by_count":47},{"id":"2005.00084","title":"Aspect-Controlled Neural Argument Generation","created":"2020-04-30","cited_by_count":43},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41},{"id":"1607.06275","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","created":"2016-07-21","cited_by_count":35},{"id":"2110.04725","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","created":"2021-10-10","cited_by_count":35},{"id":"2012.15688","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","created":"2020-12-31","cited_by_count":31},{"id":"2110.03888","title":"M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining","created":"2021-10-08","cited_by_count":31},{"id":"2105.01279","title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","created":"2021-05-04","cited_by_count":22},{"id":"2004.03116","title":"A Sentence Cloze Dataset for Chinese Machine Reading Comprehension","created":"2020-04-07","cited_by_count":14},{"id":"1711.07010","title":"A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text","created":"2017-11-19","cited_by_count":13},{"id":"1607.02250","title":"Consensus Attention-based Neural Networks for Chinese Reading Comprehension","created":"2016-07-08","cited_by_count":12},{"id":"2104.02704","title":"Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge","created":"2021-04-06","cited_by_count":10},{"id":"2107.09305","title":"Follow Your Path: a Progressive Method for Knowledge Distillation","created":"2021-07-20","cited_by_count":10},{"id":"1709.08299","title":"Dataset for the First Evaluation on Chinese Machine Reading Comprehension","created":"2017-09-25","cited_by_count":9},{"id":"2106.02241","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","created":"2021-06-04","cited_by_count":8},{"id":"2011.13573","title":"Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learning","created":"2020-11-27","cited_by_count":6},{"id":"2112.02752","title":"End-to-end Adaptive Distributed Training on PaddlePaddle","created":"2021-12-06","cited_by_count":5},{"id":"2004.14996","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","created":"2020-04-30","cited_by_count":4}],"next_cursor":null}