{"list":"other","total":52,"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":"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"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":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"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":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"1606.04586","title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning","created":"2016-06-14","cited_by_count":441},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"1909.11764","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","created":"2019-09-25","cited_by_count":264},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"2009.10195","title":"SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness","created":"2020-09-21","cited_by_count":96},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82},{"id":"2109.07589","title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","created":"2021-09-15","cited_by_count":64},{"id":"1906.03291","title":"Understanding Generalization through Visualizations","created":"2019-06-07","cited_by_count":54},{"id":"1904.09521","title":"Few-Shot NLG with Pre-Trained Language Model","created":"2019-04-21","cited_by_count":52},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44},{"id":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40},{"id":"2106.08062","title":"SSMix: Saliency-Based Span Mixup for Text Classification","created":"2021-06-15","cited_by_count":39},{"id":"1809.02255","title":"Adversarial Domain Adaptation for Duplicate Question Detection","created":"2018-09-07","cited_by_count":30},{"id":"2106.11575","title":"Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering","created":"2021-06-22","cited_by_count":27},{"id":"2109.05782","title":"Effectiveness of Pre-training for Few-shot Intent Classification","created":"2021-09-13","cited_by_count":27},{"id":"1908.09209","title":"Adversarial Domain Adaptation for Machine Reading Comprehension","created":"2019-08-24","cited_by_count":21},{"id":"2005.00791","title":"KinGDOM: Knowledge-Guided DOMain adaptation for sentiment analysis","created":"2020-05-02","cited_by_count":16},{"id":"2005.11355","title":"Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation","created":"2020-05-22","cited_by_count":13},{"id":"2006.05602","title":"Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis","created":"2020-06-10","cited_by_count":10},{"id":"2104.07284","title":"Consistency Training with Virtual Adversarial Discrete Perturbation","created":"2021-04-15","cited_by_count":9},{"id":"2104.09261","title":"Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection","created":"2021-04-19","cited_by_count":6},{"id":"1805.09302","title":"Input and Weight Space Smoothing for Semi-supervised Learning","created":"2018-05-23","cited_by_count":4},{"id":"2207.04564","title":"Domain Confused Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-07-10","cited_by_count":4},{"id":"1909.06737","title":"Understanding and Improving Virtual Adversarial Training","created":"2019-09-15","cited_by_count":2}],"next_cursor":null}