{"total":131,"rows":[{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"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":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"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":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"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":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"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":"2108.13230","title":"AEDA: An Easier Data Augmentation Technique for Text Classification","created":"2021-08-30","cited_by_count":67,"area":null},{"id":"2202.05144","title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","created":"2022-02-10","cited_by_count":62,"area":null},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2109.03856","title":"Local Augmentation for Graph Neural Networks","created":"2021-09-08","cited_by_count":53,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"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":"2103.02227","title":"Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing","created":"2021-03-03","cited_by_count":33,"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":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29,"area":null},{"id":"2109.02167","title":"Robust Attentive Deep Neural Network for Exposing GAN-generated Faces","created":"2021-09-05","cited_by_count":28,"area":null},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"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":"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":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18,"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":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2305.11096","title":"Cross-modality Data Augmentation for End-to-End Sign Language Translation","created":"2023-05-18","cited_by_count":16,"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":"2109.01758","title":"Data Augmentation for Cross-Domain Named Entity Recognition","created":"2021-09-04","cited_by_count":14,"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":"2208.14558","title":"Augraphy: A Data Augmentation Library for Document Images","created":"2022-08-30","cited_by_count":14,"area":null},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14,"area":null},{"id":"2106.11375","title":"Phrase-level Active Learning for Neural Machine Translation","created":"2021-06-21","cited_by_count":13,"area":null},{"id":"2204.06812","title":"Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation","created":"2022-04-14","cited_by_count":13,"area":null},{"id":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","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":"2206.03933","title":"TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2105.01691","title":"Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution","created":"2021-05-04","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":"2111.15112","title":"AugLiChem: Data Augmentation Library of Chemical Structures for Machine Learning","created":"2021-11-30","cited_by_count":10,"area":null},{"id":"2211.13638","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2103.01534","title":"Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation","created":"2021-03-02","cited_by_count":9,"area":null},{"id":"2104.01393","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","created":"2021-04-03","cited_by_count":9,"area":null},{"id":"2101.11753","title":"ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification","created":"2021-01-28","cited_by_count":8,"area":null},{"id":"2102.08310","title":"Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation","created":"2021-02-16","cited_by_count":8,"area":null},{"id":"2103.16911","title":"Few-shot learning through contextual data augmentation","created":"2021-03-31","cited_by_count":8,"area":null},{"id":"2109.03645","title":"Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach","created":"2021-09-08","cited_by_count":8,"area":null},{"id":"2202.12875","title":"DataLab: A Platform for Data Analysis and Intervention","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2203.01248","title":"WaveY-Net: Physics-augmented deep learning for high-speed electromagnetic simulation and optimization","created":"2022-03-02","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":"2504.01919","title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2505.04531","title":"Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review","created":"2025-05-07","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":"2211.07906","title":"Hierarchical Phrase-based Sequence-to-Sequence Learning","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2306.00253","title":"AfriNames: Most ASR models \"butcher\" African Names","created":"2023-06-01","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":"2103.00293","title":"N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking","created":"2021-02-27","cited_by_count":6,"area":null},{"id":"2409.14285","title":"ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2103.14542","title":"Unsupervised Document Embedding via Contrastive Augmentation","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2109.05793","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","created":"2021-09-13","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":"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":"2305.12786","title":"Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2411.15175","title":"ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?","created":"2024-11-18","cited_by_count":5,"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":"2112.06096","title":"Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts","created":"2021-12-11","cited_by_count":4,"area":null},{"id":"2305.17404","title":"Parallel Corpus for Indigenous Language Translation: Spanish-Mazatec and Spanish-Mixtec","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2310.13675","title":"On Synthetic Data for Back Translation","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2401.13085","title":"IndiText Boost: Text Augmentation for Low Resource India Languages","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2405.11971","title":"Data Augmentation for Text-based Person Retrieval Using Large Language Models","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2106.05634","title":"Exploring Unsupervised Pretraining Objectives for Machine Translation","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2106.08582","title":"Alternated Training with Synthetic and Authentic Data for Neural Machine Translation","created":"2021-06-16","cited_by_count":3,"area":null},{"id":"2111.04079","title":"Variance-Aware Machine Translation Test Sets","created":"2021-11-07","cited_by_count":3,"area":null},{"id":"2201.11016","title":"Recency Dropout for Recurrent Recommender Systems","created":"2022-01-26","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":"2305.09608","title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2505.02463","title":"Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2101.01628","title":"Local Translation Services for Neglected Languages","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2109.04746","title":"Counterfactual Adversarial Learning with Representation Interpolation","created":"2021-09-10","cited_by_count":2,"area":null},{"id":"2110.13231","title":"Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2201.02009","title":"PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2205.08722","title":"Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation","created":"2022-05-18","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":"2311.02355","title":"TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2402.01939","title":"A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2408.09075","title":"Improving Rare Word Translation With Dictionaries and Attention Masking","created":"2024-08-17","cited_by_count":2,"area":null},{"id":"2501.19018","title":"Scalable Multi-phase Word Embedding Using Conjunctive Propositional Clauses","created":"2025-01-31","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":"2102.05067","title":"The Role of the Input in Natural Language Video Description","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2104.10375","title":"PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation","created":"2021-04-21","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":"2210.00320","title":"MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation","created":"2022-10-01","cited_by_count":1,"area":null},{"id":"2211.07534","title":"High-Resource Methodological Bias in Low-Resource Investigations","created":"2022-11-14","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}],"next_cursor":"100"}