{"list":"other","total":68,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"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":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"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":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"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":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114},{"id":"1707.05928","title":"Deep Active Learning for Named Entity Recognition","created":"2017-07-19","cited_by_count":108},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"1911.03681","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","created":"2019-11-09","cited_by_count":96},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2008.07267","title":"A Survey of Active Learning for Text Classification using Deep Neural Networks","created":"2020-08-17","cited_by_count":50},{"id":"2109.03630","title":"Discrete and Soft Prompting for Multilingual Models","created":"2021-09-08","cited_by_count":49},{"id":"2012.15682","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","created":"2020-12-31","cited_by_count":45},{"id":"2010.02584","title":"Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start","created":"2020-10-06","cited_by_count":44},{"id":"2012.06154","title":"ParsiNLU: A Suite of Language Understanding Challenges for Persian","created":"2020-12-11","cited_by_count":42},{"id":"2009.10259","title":"ALICE: Active Learning with Contrastive Natural Language Explanations","created":"2020-09-22","cited_by_count":36},{"id":"1911.03243","title":"Controlled Crowdsourcing for High-Quality QA-SRL Annotation","created":"2019-11-08","cited_by_count":34},{"id":"2109.04645","title":"CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-09-10","cited_by_count":30},{"id":"2109.04711","title":"Pre-train or Annotate? Domain Adaptation with a Constrained Budget","created":"2021-09-10","cited_by_count":27},{"id":"1904.09688","title":"Fine-Grained Argument Unit Recognition and Classification","created":"2019-04-22","cited_by_count":26},{"id":"2109.04282","title":"Cartography Active Learning","created":"2021-09-09","cited_by_count":26},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23},{"id":"2004.12198","title":"Quantifying the Contextualization of Word Representations with Semantic Class Probing","created":"2020-04-25","cited_by_count":18},{"id":"2108.12589","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-08-28","cited_by_count":18},{"id":"1806.02418","title":"Finding Convincing Arguments Using Scalable Bayesian Preference Learning","created":"2018-06-06","cited_by_count":17},{"id":"2005.04470","title":"Empowering Active Learning to Jointly Optimize System and User Demands","created":"2020-05-09","cited_by_count":10},{"id":"2106.02382","title":"Annotation Curricula to Implicitly Train Non-Expert Annotators","created":"2021-06-04","cited_by_count":8},{"id":"1809.08888","title":"Empirical Methodology for Crowdsourcing Ground Truth","created":"2018-09-24","cited_by_count":7}],"next_cursor":null}