{"total":24,"rows":[{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"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":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2212.10400","title":"Contrastive Learning Reduces Hallucination in Conversations","created":"2022-12-20","cited_by_count":40,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"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":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","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":"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":"2211.07906","title":"Hierarchical Phrase-based Sequence-to-Sequence Learning","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2110.08538","title":"Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing","created":"2021-10-16","cited_by_count":5,"area":null},{"id":"2202.06409","title":"Distribution augmentation for low-resource expressive text-to-speech","created":"2022-02-13","cited_by_count":5,"area":null},{"id":"2401.17703","title":"WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2310.00277","title":"A Unified Framework for Generative Data Augmentation: A Comprehensive Survey","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2408.16756","title":"How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","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":"2402.13372","title":"EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2406.09662","title":"Learning Language Structures through Grounding","created":"2024-06-14","cited_by_count":2,"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":"2211.10944","title":"Feature Weaken: Vicinal Data Augmentation for Classification","created":"2022-11-20","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}],"next_cursor":null}