{"total":42,"rows":[{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2109.03856","title":"Local Augmentation for Graph Neural Networks","created":"2021-09-08","cited_by_count":53,"area":null},{"id":"2304.08460","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","created":"2023-04-17","cited_by_count":47,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2103.02227","title":"Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing","created":"2021-03-03","cited_by_count":33,"area":null},{"id":"2103.14453","title":"Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers","created":"2021-03-26","cited_by_count":24,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2109.01758","title":"Data Augmentation for Cross-Domain Named Entity Recognition","created":"2021-09-04","cited_by_count":14,"area":null},{"id":"2111.09618","title":"To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP","created":"2021-11-18","cited_by_count":12,"area":null},{"id":"2301.02427","title":"Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2108.11703","title":"Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation","created":"2021-08-26","cited_by_count":10,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2305.16663","title":"GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2204.11205","title":"EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification","created":"2022-04-24","cited_by_count":7,"area":null},{"id":"2404.00303","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","created":"2024-03-30","cited_by_count":7,"area":null},{"id":"2210.10343","title":"Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2106.03952","title":"Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2311.07497","title":"Multilingual Nonce Dependency Treebanks: Understanding how Language Models represent and process syntactic structure","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2401.13085","title":"IndiText Boost: Text Augmentation for Low Resource India Languages","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2201.11374","title":"Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2306.12907","title":"xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages","created":"2023-06-22","cited_by_count":3,"area":null},{"id":"2409.19620","title":"DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2111.04099","title":"Developing neural machine translation models for Hungarian-English","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2301.12289","title":"Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformer","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2206.06868","title":"Natural Language Sentence Generation from API Specifications","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2208.02169","title":"SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences","created":"2022-08-03","cited_by_count":0,"area":null},{"id":"2209.02267","title":"Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2304.04539","title":"UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Posts","created":"2023-04-10","cited_by_count":0,"area":null},{"id":"2310.09705","title":"SGA: A Graph Augmentation Method for Signed Graph Neural Networks","created":"2023-10-15","cited_by_count":0,"area":null},{"id":"2311.04535","title":"RankAug: Augmented data ranking for text classification","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2311.09505","title":"SegMix: A Simple Structure-Aware Data Augmentation Method","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2406.06127","title":"Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2410.06944","title":"CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2411.18755","title":"Cyber-Attack Technique Classification Using Two-Stage Trained Large Language Models","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2502.05923","title":"ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2606.18780","title":"SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.04808","title":"A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}