{"list":"other","total":74,"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":"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"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":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"1804.06059","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","created":"2018-04-17","cited_by_count":286},{"id":"2104.02395","title":"Ensemble deep learning: A review","created":"2021-04-06","cited_by_count":284},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"1910.09753","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","created":"2019-10-22","cited_by_count":184},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"1705.00440","title":"Data Augmentation for Low-Resource Neural Machine Translation","created":"2017-05-01","cited_by_count":139},{"id":"2010.08240","title":"Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks","created":"2020-10-16","cited_by_count":138},{"id":"2005.02324","title":"Neural CRF Model for Sentence Alignment in Text Simplification","created":"2020-05-05","cited_by_count":106},{"id":"1906.00080","title":"Gmail Smart Compose: Real-Time Assisted Writing","created":"2019-05-17","cited_by_count":98},{"id":"1908.08167","title":"Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering","created":"2019-08-22","cited_by_count":96},{"id":"1709.01643","title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","created":"2017-09-06","cited_by_count":91},{"id":"1806.04734","title":"Delta-encoder: an effective sample synthesis method for few-shot object recognition","created":"2018-06-12","cited_by_count":89},{"id":"1702.01923","title":"Comparative Study of CNN and RNN for Natural Language Processing","created":"2017-02-07","cited_by_count":82},{"id":"2006.06402","title":"CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP","created":"2020-06-11","cited_by_count":79},{"id":"1703.02573","title":"Data Noising as Smoothing in Neural Network Language Models","created":"2017-03-07","cited_by_count":78},{"id":"1910.02677","title":"Controllable Sentence Simplification","created":"2019-10-07","cited_by_count":78},{"id":"2010.11683","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","created":"2020-10-22","cited_by_count":76},{"id":"1808.07512","title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","created":"2018-08-22","cited_by_count":72},{"id":"1807.01554","title":"Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding","created":"2018-07-04","cited_by_count":68},{"id":"2108.13230","title":"AEDA: An Easier Data Augmentation Technique for Text Classification","created":"2021-08-30","cited_by_count":67},{"id":"1904.01172","title":"Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches","created":"2019-04-02","cited_by_count":65},{"id":"1806.03852","title":"Data augmentation instead of explicit regularization","created":"2018-06-11","cited_by_count":63},{"id":"1911.07176","title":"Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering","created":"2019-11-17","cited_by_count":59},{"id":"1711.00279","title":"Paraphrase Generation with Deep Reinforcement Learning","created":"2017-11-01","cited_by_count":58},{"id":"1906.03785","title":"Generalized Data Augmentation for Low-Resource Translation","created":"2019-06-10","cited_by_count":53},{"id":"2004.11546","title":"Generative Data Augmentation for Commonsense Reasoning","created":"2020-04-24","cited_by_count":49},{"id":"2012.02952","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","created":"2020-12-05","cited_by_count":47},{"id":"1903.09460","title":"Data Augmentation via Dependency Tree Morphing for Low-Resource Languages","created":"2019-03-22","cited_by_count":45},{"id":"2010.01764","title":"How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?","created":"2020-10-05","cited_by_count":41},{"id":"1812.04718","title":"Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs","created":"2018-12-05","cited_by_count":40},{"id":"1808.09468","title":"Learning To Split and Rephrase From Wikipedia Edit History","created":"2018-08-28","cited_by_count":38},{"id":"2004.02594","title":"Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight","created":"2020-04-06","cited_by_count":34},{"id":"1911.02984","title":"The TechQA Dataset","created":"2019-11-08","cited_by_count":30},{"id":"2004.14769","title":"Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation","created":"2020-04-30","cited_by_count":27},{"id":"1806.07304","title":"Dynamic Multi-Level Multi-Task Learning for Sentence Simplification","created":"2018-06-19","cited_by_count":25},{"id":"1707.06971","title":"Split and Rephrase","created":"2017-07-21","cited_by_count":24},{"id":"1909.00088","title":"Keep Calm and Switch On! Preserving Sentiment and Fluency in Semantic Text Exchange","created":"2019-08-30","cited_by_count":19},{"id":"2007.13876","title":"Semi-Supervised Learning with Data Augmentation for End-to-End ASR","created":"2020-07-27","cited_by_count":19},{"id":"1805.06962","title":"Counterexample-Guided Data Augmentation","created":"2018-05-17","cited_by_count":15},{"id":"2005.00352","title":"MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases","created":"2020-05-01","cited_by_count":15},{"id":"1909.11241","title":"Atalaya at TASS 2019: Data Augmentation and Robust Embeddings for Sentiment Analysis","created":"2019-09-25","cited_by_count":12},{"id":"2010.11966","title":"Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data","created":"2020-10-22","cited_by_count":11},{"id":"2009.10778","title":"On Data Augmentation for Extreme Multi-label Classification","created":"2020-09-22","cited_by_count":10},{"id":"2004.13952","title":"Data Augmentation for Spoken Language Understanding via Pretrained Language Models","created":"2020-04-29","cited_by_count":9},{"id":"2007.02033","title":"Text Data Augmentation: Towards better detection of spear-phishing emails","created":"2020-07-04","cited_by_count":9},{"id":"2009.12452","title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context","created":"2020-09-25","cited_by_count":8},{"id":"2011.01856","title":"Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory","created":"2020-11-03","cited_by_count":8},{"id":"1703.09013","title":"A Sentence Simplification System for Improving Relation Extraction","created":"2017-03-27","cited_by_count":7},{"id":"1901.04420","title":"Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness","created":"2019-01-14","cited_by_count":7},{"id":"2106.04134","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","created":"2021-06-08","cited_by_count":7},{"id":"2012.02420","title":"Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation","created":"2020-12-04","cited_by_count":5},{"id":"1808.09381","title":"Understanding Back-Translation at Scale","created":"2018-08-28","cited_by_count":2}],"next_cursor":null}