{"total":37,"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":"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":"2304.13861","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","created":"2023-04-26","cited_by_count":35,"area":null},{"id":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32,"area":null},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30,"area":null},{"id":"2301.02830","title":"Image Data Augmentation Approaches: A Comprehensive Survey and Future directions","created":"2023-01-07","cited_by_count":23,"area":null},{"id":"2501.18845","title":"Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities","created":"2025-01-31","cited_by_count":22,"area":null},{"id":"2306.11892","title":"Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2104.06669","title":"NAREOR: The Narrative Reordering Problem","created":"2021-04-14","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":"2112.02807","title":"MDPFuzz: Testing Models Solving Markov Decision Processes","created":"2021-12-06","cited_by_count":12,"area":null},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12,"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":"2109.03892","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","created":"2021-09-08","cited_by_count":9,"area":null},{"id":"2108.06643","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","created":"2021-08-15","cited_by_count":8,"area":null},{"id":"2305.17968","title":"Data Augmentation for Low-Resource Keyphrase Generation","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2210.04191","title":"CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2106.02833","title":"Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2209.06275","title":"PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically","created":"2022-09-13","cited_by_count":6,"area":null},{"id":"2204.08198","title":"UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2209.01560","title":"Selective Text Augmentation with Word Roles for Low-Resource Text Classification","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2405.08729","title":"Targeted Augmentation for Low-Resource Event Extraction","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2109.09825","title":"Data Augmentation Methods for Anaphoric Zero Pronouns","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2204.02633","title":"DAGAM: Data Augmentation with Generation And Modification","created":"2022-04-06","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":"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":"2605.04344","title":"Perturbation is All You Need for Extrapolating Language Models","created":"2026-05-05","cited_by_count":2,"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":"2203.17110","title":"Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?","created":"2022-03-31","cited_by_count":1,"area":null},{"id":"2205.09661","title":"Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2209.07752","title":"PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2503.23576","title":"The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR","created":"2025-03-30","cited_by_count":1,"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":"2605.13284","title":"Learning Perturbations to Extrapolate Your LLM","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}