{"total":76,"rows":[{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"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":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"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":"2109.11406","title":"Named Entity Recognition and Classification on Historical Documents: A Survey","created":"2021-09-23","cited_by_count":47,"area":null},{"id":"2108.13655","title":"MELM: Data Augmentation with Masked Entity Language Modeling for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":"2109.05003","title":"Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training","created":"2021-09-10","cited_by_count":41,"area":null},{"id":"2109.06415","title":"Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction","created":"2021-09-14","cited_by_count":33,"area":null},{"id":"2205.09651","title":"Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT","created":"2022-05-19","cited_by_count":33,"area":null},{"id":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29,"area":null},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26,"area":null},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"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":"2204.04391","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","created":"2022-04-09","cited_by_count":17,"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":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"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":"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":"2402.10573","title":"LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty","created":"2024-02-16","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":"2402.14568","title":"LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition","created":"2024-02-22","cited_by_count":11,"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":"2306.00928","title":"ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2404.00415","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","created":"2024-03-30","cited_by_count":9,"area":null},{"id":"2302.03512","title":"A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends","created":"2023-02-07","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":"2406.04286","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2206.13607","title":"Improved Text Classification via Test-Time Augmentation","created":"2022-06-27","cited_by_count":7,"area":null},{"id":"2208.11464","title":"FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition","created":"2022-08-24","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":"2305.17854","title":"E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition","created":"2023-05-29","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":"2305.10647","title":"BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2212.14657","title":"Linear programming word problems formulation using EnsembleCRF NER labeler and T5 text generator with data augmentations","created":"2022-12-30","cited_by_count":4,"area":null},{"id":"2204.11406","title":"Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting","created":"2022-04-25","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":"2212.13939","title":"Data Augmentation using Transformers and Similarity Measures for Improving Arabic Text Classification","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2302.06448","title":"Joint Span Segmentation and Rhetorical Role Labeling with Data Augmentation for Legal Documents","created":"2023-02-13","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":"2407.02062","title":"Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2412.08434","title":"Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2106.01635","title":"Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children's mindreading ability","created":"2021-06-03","cited_by_count":2,"area":null},{"id":"2111.05196","title":"NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation","created":"2021-11-09","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":"2204.07459","title":"Qtrade AI at SemEval-2022 Task 11: An Unified Framework for Multilingual NER Task","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2210.07916","title":"Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition","created":"2022-10-14","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":"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":"2111.10584","title":"Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles","created":"2021-11-20","cited_by_count":1,"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":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2302.04555","title":"Data Augmentation for Robust Character Detection in Fantasy Novels","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2307.07025","title":"Data Augmentation for Machine Translation via Dependency Subtree Swapping","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2506.03593","title":"Is linguistically-motivated data augmentation worth it?","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2110.08430","title":"Metadata Shaping: Natural Language Annotations for the Tail","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2208.06957","title":"Syntax-driven Data Augmentation for Named Entity Recognition","created":"2022-08-15","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":"2212.10047","title":"An Augmentation Strategy for Visually Rich Documents","created":"2022-12-20","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":"2305.18152","title":"Extrinsic Factors Affecting the Accuracy of Biomedical NER","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2305.19497","title":"Towards Flow Graph Prediction of Open-Domain Procedural Texts","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2307.07417","title":"RoPDA: Robust Prompt-based Data Augmentation for Low-Resource Named Entity Recognition","created":"2023-07-11","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":"2406.12779","title":"Composited-Nested-Learning with Data Augmentation for Nested Named Entity Recognition","created":"2024-06-18","cited_by_count":0,"area":null},{"id":"2410.12750","title":"Comparative Analysis of Extrinsic Factors for NER in French","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2412.05388","title":"CALICO: Conversational Agent Localization via Synthetic Data Generation","created":"2024-12-06","cited_by_count":0,"area":"agents"},{"id":"2507.15864","title":"Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2510.04001","title":"Named Entity Recognition in COVID-19 tweets with Entity Knowledge Augmentation","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.20143","title":"SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Gird-based Discontinuous NER Models","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2603.00840","title":"Learning Nested Named Entity Recognition from Flat Annotations","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2604.12477","title":"Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.12540","title":"When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP","created":"2026-04-14","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":"2606.21890","title":"Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2610.03268","title":"Shrome at Touch\\'e: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}