{"total":68,"rows":[{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"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":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"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":"2106.00291","title":"Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking","created":"2021-06-01","cited_by_count":35,"area":null},{"id":"2110.06800","title":"SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems","created":"2021-10-13","cited_by_count":34,"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":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2204.09867","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","created":"2022-04-21","cited_by_count":25,"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":"2105.14454","title":"NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation","created":"2021-05-30","cited_by_count":16,"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":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10,"area":null},{"id":"2305.16663","title":"GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2306.02842","title":"Improving Conversational Recommendation Systems via Counterfactual Data Simulation","created":"2023-06-05","cited_by_count":10,"area":null},{"id":"2207.06872","title":"Data Augmentation for Low-Resource Quechua ASR Improvement","created":"2022-07-14","cited_by_count":9,"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":"2210.12096","title":"Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play","created":"2022-10-21","cited_by_count":9,"area":null},{"id":"2308.14533","title":"A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER","created":"2023-08-28","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":"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":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2110.00046","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2210.16838","title":"Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2404.00303","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","created":"2024-03-30","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":"2106.07343","title":"Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling","created":"2021-05-25","cited_by_count":6,"area":null},{"id":"2204.00291","title":"Text-To-Speech Data Augmentation for Low Resource Speech Recognition","created":"2022-04-01","cited_by_count":6,"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":"2404.11095","title":"Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues","created":"2024-04-17","cited_by_count":6,"area":"alignment"},{"id":"2408.06044","title":"DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversation","created":"2024-08-12","cited_by_count":6,"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":"2302.11349","title":"Steerable Equivariant Representation Learning","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2110.11514","title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","created":"2021-10-21","cited_by_count":3,"area":null},{"id":"2207.08179","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2210.12942","title":"Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?","created":"2022-10-24","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":"2303.09719","title":"Learning towards Selective Data Augmentation for Dialogue Generation","created":"2023-03-17","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":"2308.12648","title":"From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2509.15373","title":"Frustratingly Easy Data Augmentation for Low-Resource ASR","created":"2025-09-18","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":"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":"2110.13231","title":"Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs","created":"2021-10-25","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":"2303.09905","title":"More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2310.10380","title":"Contextual Data Augmentation for Task-Oriented Dialog Systems","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2108.08451","title":"Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models","created":"2021-08-19","cited_by_count":1,"area":null},{"id":"2110.05892","title":"Investigation on Data Adaptation Techniques for Neural Named Entity Recognition","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2111.14709","title":"Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching","created":"2021-11-29","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":"2209.00797","title":"Random Text Perturbations Work, but not Always","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2304.13902","title":"Controllable Data Augmentation for Context-Dependent Text-to-SQL","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2305.01323","title":"Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2508.06886","title":"Score Before You Speak: Improving Persona Consistency in Dialogue Generation using Response Quality Scores","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2306.04823","title":"Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems","created":"2023-06-07","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":"2308.04109","title":"I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2310.06404","title":"Hexa: Self-Improving for Knowledge-Grounded Dialogue System","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2311.04535","title":"RankAug: Augmented data ranking for text classification","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2406.06127","title":"Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2604.27182","title":"Preserving Temporal Dynamics in Time Series Generation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.23440","title":"SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2610.13807","title":"Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}