{"list":"other","total":51,"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":"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"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":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1905.00877","title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","created":"2019-05-02","cited_by_count":183},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","cited_by_count":156},{"id":"2004.08994","title":"Adversarial Training for Large Neural Language Models","created":"2020-04-20","cited_by_count":111},{"id":"1906.02443","title":"Robust Neural Machine Translation with Doubly Adversarial Inputs","created":"2019-06-06","cited_by_count":106},{"id":"2010.02329","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","created":"2020-10-05","cited_by_count":92},{"id":"1805.02917","title":"Interpretable Adversarial Perturbation in Input Embedding Space for Text","created":"2018-05-08","cited_by_count":67},{"id":"2007.06661","title":"Robustness to Spurious Correlations via Human Annotations","created":"2020-07-13","cited_by_count":62},{"id":"1908.05147","title":"SG-Net: Syntax-Guided Machine Reading Comprehension","created":"2019-08-14","cited_by_count":52},{"id":"1906.03805","title":"Improving Neural Language Modeling via Adversarial Training","created":"2019-06-10","cited_by_count":49},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46},{"id":"2005.00742","title":"Hard-Coded Gaussian Attention for Neural Machine Translation","created":"2020-05-02","cited_by_count":42},{"id":"2106.00149","title":"HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization","created":"2021-05-31","cited_by_count":32},{"id":"2105.14553","title":"Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice","created":"2021-05-30","cited_by_count":30},{"id":"2012.14710","title":"Code Summarization with Structure-induced Transformer","created":"2020-12-29","cited_by_count":29},{"id":"1906.04135","title":"A Multi-task Approach for Named Entity Recognition in Social Media Data","created":"2019-06-10","cited_by_count":18},{"id":"2010.02705","title":"Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation","created":"2020-10-06","cited_by_count":14},{"id":"2203.12709","title":"Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation","created":"2022-03-23","cited_by_count":12},{"id":"2004.05568","title":"Pre-training Text Representations as Meta Learning","created":"2020-04-12","cited_by_count":5},{"id":"2104.04692","title":"Not All Attention Is All You Need","created":"2021-04-10","cited_by_count":5},{"id":"2108.12805","title":"DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks","created":"2021-08-29","cited_by_count":2}],"next_cursor":null}