{"total":107,"rows":[{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"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":"2109.04380","title":"ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding","created":"2021-09-09","cited_by_count":74,"area":null},{"id":"2108.13230","title":"AEDA: An Easier Data Augmentation Technique for Text Classification","created":"2021-08-30","cited_by_count":67,"area":null},{"id":"2109.08914","title":"Text Detoxification using Large Pre-trained Neural Models","created":"2021-09-18","cited_by_count":52,"area":null},{"id":"2202.12499","title":"PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks","created":"2022-02-25","cited_by_count":51,"area":null},{"id":"2204.01959","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","created":"2022-04-05","cited_by_count":49,"area":null},{"id":"2106.06168","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","created":"2021-06-11","cited_by_count":42,"area":"distill"},{"id":"2108.13655","title":"MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER","created":"2021-08-31","cited_by_count":42,"area":null},{"id":"2207.07522","title":"Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation","created":"2022-07-15","cited_by_count":38,"area":null},{"id":"2105.11098","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","created":"2021-05-24","cited_by_count":34,"area":null},{"id":"2304.14334","title":"ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT","created":"2023-04-27","cited_by_count":32,"area":null},{"id":"2401.15422","title":"A Survey on Data Augmentation in Large Model Era","created":"2024-01-27","cited_by_count":31,"area":"diffusion"},{"id":"2310.14192","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2109.03079","title":"GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation","created":"2021-09-07","cited_by_count":20,"area":null},{"id":"2310.18365","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2404.17642","title":"Empowering Large Language Models for Textual Data Augmentation","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2310.07756","title":"Self-supervised Representation Learning From Random Data Projectors","created":"2023-10-11","cited_by_count":15,"area":null},{"id":"2111.09064","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","created":"2021-11-17","cited_by_count":14,"area":null},{"id":"2208.08110","title":"PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2105.09052","title":"Methods for Detoxification of Texts for the Russian Language","created":"2021-05-19","cited_by_count":13,"area":null},{"id":"2202.13840","title":"Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks","created":"2022-02-28","cited_by_count":13,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"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":"2204.07832","title":"A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis","created":"2022-04-16","cited_by_count":12,"area":null},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2211.10330","title":"GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation","created":"2022-11-18","cited_by_count":11,"area":null},{"id":"2104.07284","title":"Consistency Training with Virtual Adversarial Discrete Perturbation","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2103.16911","title":"Few-shot learning through contextual data augmentation","created":"2021-03-31","cited_by_count":8,"area":null},{"id":"2204.07837","title":"BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation","created":"2022-04-16","cited_by_count":8,"area":null},{"id":"2408.16502","title":"LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?","created":"2024-08-29","cited_by_count":8,"area":null},{"id":"2112.10064","title":"Data Augmentation for Mental Health Classification on Social Media","created":"2021-12-19","cited_by_count":7,"area":null},{"id":"2210.08855","title":"PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2112.13969","title":"LINDA: Unsupervised Learning to Interpolate in Natural Language Processing","created":"2021-12-28","cited_by_count":6,"area":null},{"id":"2203.02951","title":"Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2022-03-06","cited_by_count":6,"area":null},{"id":"2407.00341","title":"Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysis","created":"2024-06-29","cited_by_count":6,"area":null},{"id":"2409.14473","title":"A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language","created":"2024-09-22","cited_by_count":6,"area":"diffusion"},{"id":"2103.14542","title":"Unsupervised Document Embedding via Contrastive Augmentation","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2201.02489","title":"Semantic-based Data Augmentation for Math Word Problems","created":"2022-01-07","cited_by_count":5,"area":null},{"id":"2203.09391","title":"When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation","created":"2022-03-17","cited_by_count":5,"area":"distill"},{"id":"2204.04711","title":"Data Augmentation for Biomedical Factoid Question Answering","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2204.12421","title":"Disambiguation of morpho-syntactic features of African American English -- the case of habitual be","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2305.04505","title":"Target-Side Augmentation for Document-Level Machine Translation","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2305.13547","title":"Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2409.03203","title":"An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification","created":"2024-09-05","cited_by_count":5,"area":null},{"id":"2507.09485","title":"Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2105.13650","title":"Data Augmentation for Text Generation Without Any Augmented Data","created":"2021-05-28","cited_by_count":4,"area":null},{"id":"2106.05141","title":"AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2109.01583","title":"Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding","created":"2021-09-03","cited_by_count":4,"area":null},{"id":"2309.04862","title":"Distributional Data Augmentation Methods for Low Resource Language","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2106.11629","title":"On Adversarial Robustness of Synthetic Code Generation","created":"2021-06-22","cited_by_count":3,"area":null},{"id":"2206.02252","title":"Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models","created":"2022-06-05","cited_by_count":3,"area":null},{"id":"2206.02734","title":"Global Mixup: Eliminating Ambiguity with Clustering","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2209.10875","title":"Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2303.09719","title":"Learning towards Selective Data Augmentation for Dialogue Generation","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2305.09598","title":"Boosting Event Extraction with Denoised Structure-to-Text Augmentation","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2306.11260","title":"A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2310.13183","title":"Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2310.15594","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2411.14896","title":"Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2101.08106","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","created":"2021-01-20","cited_by_count":2,"area":"distill"},{"id":"2110.07174","title":"Context-gloss Augmentation for Improving Word Sense Disambiguation","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2110.13016","title":"Generating artificial texts as substitution or complement of training data","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2204.02653","title":"Using Synthetic Data for Conversational Response Generation in Low-resource Settings","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2301.08606","title":"Data Augmentation for Modeling Human Personality: The Dexter Machine","created":"2023-01-20","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":"2302.12784","title":"STA: Self-controlled Text Augmentation for Improving Text Classifications","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2308.00939","title":"Feature-aware conditional GAN for category text generation","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2310.18930","title":"Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2402.14895","title":"On Evaluation Protocols for Data Augmentation in a Limited Data Scenario","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2411.04059","title":"Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2507.14590","title":"Backtranslation and paraphrasing in the LLM era? Comparing data augmentation methods for emotion classification","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2110.05892","title":"Investigation on Data Adaptation Techniques for Neural Named Entity Recognition","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2202.02566","title":"LST: Lexicon-Guided Self-Training for Few-Shot Text Classification","created":"2022-02-05","cited_by_count":1,"area":null},{"id":"2202.13363","title":"Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2204.13638","title":"Russian Texts Detoxification with Levenshtein Editing","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2305.09287","title":"Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2305.13535","title":"Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2306.01931","title":"Simple Data Augmentation Techniques for Chinese Disease Normalization","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2310.14429","title":"Text generation for dataset augmentation in security classification tasks","created":"2023-10-22","cited_by_count":1,"area":null},{"id":"2402.05584","title":"AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.15512","title":"Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2406.05190","title":"Evaluating the Effectiveness of Data Augmentation for Emotion Classification in Low-Resource Settings","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2409.20498","title":"Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation","created":"2024-09-30","cited_by_count":1,"area":"distill"},{"id":"2508.21083","title":"CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2109.11834","title":"A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification","created":"2021-09-24","cited_by_count":0,"area":null},{"id":"2206.11219","title":"Understanding the Properties of Generated Corpora","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2211.02971","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","created":"2022-11-05","cited_by_count":0,"area":null},{"id":"2211.16353","title":"Outfit Generation and Recommendation -- An Experimental Study","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2303.02758","title":"WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2306.04823","title":"Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2308.04109","title":"I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2402.06766","title":"Evaluation Metrics for Text Data Augmentation in NLP","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2403.20015","title":"Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion","created":"2024-03-29","cited_by_count":0,"area":null},{"id":"2405.13013","title":"Amplifying Aspect-Sentence Awareness: A Novel Approach for Aspect-Based Sentiment Analysis","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2409.02751","title":"A Comparative Study of Pre-training and Self-training","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2409.17191","title":"An Effective, Robust and Fairness-aware Hate Speech Detection Framework","created":"2024-09-25","cited_by_count":0,"area":null}],"next_cursor":"100"}