{"list":"other","total":66,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"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":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2102.09554","title":"Delving into Deep Imbalanced Regression","created":"2021-02-18","cited_by_count":158},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"2007.09654","title":"Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets","created":"2020-07-19","cited_by_count":122},{"id":"1512.05830","title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","created":"2015-12-18","cited_by_count":115},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"2102.01373","title":"An Improved Baseline for Sentence-level Relation Extraction","created":"2021-02-02","cited_by_count":81},{"id":"1903.01306","title":"Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks","created":"2019-03-04","cited_by_count":61},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60},{"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":"2109.05427","title":"Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification","created":"2021-09-12","cited_by_count":43},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38},{"id":"2012.01687","title":"Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition","created":"2020-12-03","cited_by_count":35},{"id":"2109.04712","title":"Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution","created":"2021-09-10","cited_by_count":35},{"id":"1504.06580","title":"Classifying Relations by Ranking with Convolutional Neural Networks","created":"2015-04-24","cited_by_count":33},{"id":"2105.00828","title":"Memorisation versus Generalisation in Pre-trained Language Models","created":"2021-04-16","cited_by_count":32},{"id":"2109.05213","title":"Uncovering Main Causalities for Long-tailed Information Extraction","created":"2021-09-11","cited_by_count":21},{"id":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19},{"id":"1711.08760","title":"Boosted Cascaded Convnets for Multilabel Classification of Thoracic Diseases in Chest Radiographs","created":"2017-11-23","cited_by_count":18},{"id":"2003.11563","title":"Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data","created":"2020-03-16","cited_by_count":14},{"id":"2104.10652","title":"TransICD: Transformer Based Code-wise Attention Model for Explainable ICD Coding","created":"2021-03-28","cited_by_count":13},{"id":"2009.12344","title":"A little goes a long way: Improving toxic language classification despite data scarcity","created":"2020-09-25","cited_by_count":12},{"id":"2008.11573","title":"Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance","created":"2020-08-26","cited_by_count":11},{"id":"2012.01285","title":"Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories","created":"2020-12-02","cited_by_count":11},{"id":"2104.08078","title":"To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning","created":"2021-04-16","cited_by_count":11},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11},{"id":"2009.07022","title":"The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis","created":"2020-09-15","cited_by_count":10},{"id":"2009.10778","title":"On Data Augmentation for Extreme Multi-label Classification","created":"2020-09-22","cited_by_count":10},{"id":"2010.12699","title":"Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary","created":"2020-10-23","cited_by_count":8},{"id":"2011.12454","title":"Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer","created":"2020-11-25","cited_by_count":8},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8},{"id":"1906.06003","title":"Cost-sensitive Regularization for Label Confusion-aware Event Detection","created":"2019-06-14","cited_by_count":5},{"id":"2109.05602","title":"Good-Enough Example Extrapolation","created":"2021-09-12","cited_by_count":5},{"id":"1907.07653","title":"Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs","created":"2019-07-17","cited_by_count":4},{"id":"1912.00342","title":"Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives","created":"2019-12-01","cited_by_count":4},{"id":"2008.10163","title":"syrapropa at SemEval-2020 Task 11: BERT-based Models Design For Propagandistic Technique and Span Detection","created":"2020-08-24","cited_by_count":4},{"id":"2105.08445","title":"DRILL: Dynamic Representations for Imbalanced Lifelong Learning","created":"2021-05-18","cited_by_count":4},{"id":"2104.06313","title":"SetConv: A New Approach for Learning from Imbalanced Data","created":"2021-04-03","cited_by_count":3},{"id":"2008.02603","title":"Data balancing for boosting performance of low-frequency classes in Spoken Language Understanding","created":"2020-08-06","cited_by_count":1},{"id":"2204.12024","title":"Reprint: a randomized extrapolation based on principal components for data augmentation","created":"2022-04-26","cited_by_count":1}],"next_cursor":null}