{"total":40,"rows":[{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"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":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"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":"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":"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":"2205.00177","title":"Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers","created":"2022-04-30","cited_by_count":9,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2109.05602","title":"Good-Enough Example Extrapolation","created":"2021-09-12","cited_by_count":5,"area":null},{"id":"2204.04711","title":"Data Augmentation for Biomedical Factoid Question Answering","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2207.11076","title":"Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence","created":"2022-07-22","cited_by_count":4,"area":null},{"id":"2204.07679","title":"DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2209.14812","title":"Named Entity Recognition in Industrial Tables using Tabular Language Models","created":"2022-09-29","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","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":"2304.12847","title":"NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2307.16609","title":"Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2401.09239","title":"DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2411.14551","title":"An Experimental Study on Data Augmentation Techniques for Named Entity Recognition on Low-Resource Domains","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2210.15172","title":"Dictionary-Assisted Supervised Contrastive Learning","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2212.05251","title":"A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2303.02577","title":"Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data","created":"2023-03-05","cited_by_count":1,"area":null},{"id":"2309.09877","title":"Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2310.17015","title":"Data Augmentation for Emotion Detection in Small Imbalanced Text Data","created":"2023-10-25","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":"2403.02504","title":"A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2102.09708","title":"Back Translation Survey for Improving Text Augmentation","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2303.02198","title":"Exploring Data Augmentation Methods on Social Media Corpora","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2306.16644","title":"Probabilistic Linguistic Knowledge and Token-level Text Augmentation","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2307.00008","title":"Investigating Masking-based Data Generation in Language Models","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2309.16175","title":"Using Weak Supervision and Data Augmentation in Question Answering","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2403.18218","title":"Leveraging Large Language Models for Fuzzy String Matching in Political Science","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2601.19124","title":"Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2605.01073","title":"Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2609.07766","title":"Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}