{"total":39,"rows":[{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130,"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":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2206.08358","title":"MixGen: A New Multi-Modal Data Augmentation","created":"2022-06-16","cited_by_count":61,"area":null},{"id":"2201.12093","title":"PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings","created":"2022-01-28","cited_by_count":29,"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":"2404.17642","title":"Empowering Large Language Models for Textual Data Augmentation","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2106.01649","title":"LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification","created":"2021-06-03","cited_by_count":16,"area":null},{"id":"2105.14897","title":"Connecting Language and Vision for Natural Language-Based Vehicle Retrieval","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2111.15112","title":"AugLiChem: Data Augmentation Library of Chemical Structures for Machine Learning","created":"2021-11-30","cited_by_count":10,"area":null},{"id":"2208.11508","title":"PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling","created":"2022-08-24","cited_by_count":9,"area":null},{"id":"2410.20796","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2108.10248","title":"Influence-guided Data Augmentation for Neural Tensor Completion","created":"2021-08-23","cited_by_count":7,"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":"2211.04928","title":"miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2305.17440","title":"Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2310.03518","title":"Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2401.01830","title":"Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling","created":"2024-01-03","cited_by_count":4,"area":null},{"id":"2403.15214","title":"InstaSynth: Opportunities and Challenges in Generating Synthetic Instagram Data with ChatGPT for Sponsored Content Detection","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2203.00354","title":"Improving Performance of Automated Essay Scoring by using back-translation essays and adjusted scores","created":"2022-03-01","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":"2306.06819","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2107.02025","title":"Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment","created":"2021-06-15","cited_by_count":2,"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":"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":"2408.13985","title":"TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2204.12024","title":"Reprint: a randomized extrapolation based on principal components for data augmentation","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2210.02941","title":"BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework","created":"2022-10-06","cited_by_count":1,"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":"2306.17020","title":"Classifying Crime Types using Judgment Documents from Social Media","created":"2023-06-29","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},{"id":"2409.17474","title":"Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.06348","title":"Harnessing the Power of Noise: A Survey of Techniques and Applications","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2507.00891","title":"MemeCMD: An Automatically Generated Chinese Multi-turn Dialogue Dataset with Contextually Retrieved Memes","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.19333","title":"PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification","created":"2026-02-22","cited_by_count":0,"area":null}],"next_cursor":null}