Survey of NLP Data Augmentation Methods Based on Large Language Models

doi:10.3778/j.issn.1673-9418.2410054

Abstract

Abstract: Currently, large language models show great potential in the field of natural language processing (NLP), but their training process relies on a large number of high-quality samples. In low-resource scenarios, the number of existing data samples can hardly support the convergence of model training as the model size keeps increasing, and this problem has inspired researchers in related fields to investigate data augmentation methods. However, traditional data enhancement methods have limited application scope and data distortion problems in the context of large models in NLP. In contrast, data enhancement methods based on large language models can address this challenge more effectively. This paper offers a comprehensive exploration of data augmentation methods for large language models in the current NLP field and adopts a comprehensive perspective to study data enhancement in the NLP domain. Firstly, the development history of traditional data enhancement methods and big language models in the NLP domain is reviewed. Then, a variety of large language model data enhancement methods in the NLP domain at this stage are summarized, and the scope of application, advantages and limitations of each method are discussed in depth. Subsequently, data enhancement evaluation methods in the field of NLP are introduced. Finally, future research directions of data enhancement methods for large language models in the NLP domain are discussed through comparative experiments and result analyses of current methods, and prospective suggestions are made.

Key words: data augmentation, large language models, natural language processing, deep learning, artificial intelligence

摘要： 当前，大语言模型在自然语言处理（NLP）领域展现出巨大的潜力，但其训练过程依赖于大量高质量样本。在低资源场景下，随着模型规模不断扩大，现有数据样本数量难以支撑模型训练收敛，这一问题激发了相关领域科研工作者对于数据增强方法的研究。然而，传统数据增强方法在NLP领域大模型背景下存在应用范围有限和数据失真的问题。相比之下，基于大语言模型的数据增强方法能够更有效地应对这一挑战。全面探讨了现阶段NLP领域大语言模型数据增强方法，采用了综合性的视角研究NLP领域数据增强。对NLP领域传统数据增强方法进行分析与总结。将现阶段NLP领域多种大语言模型数据增强方法归纳总结，并深入探讨了每一种方法的适用范围、优点以及局限性。介绍了NLP领域数据增强评估方法。通过对当前方法的对比实验和结果分析讨论了NLP领域大语言模型数据增强方法的未来研究方向，并提出了前瞻性建议。

关键词: 数据增强方法, 大语言模型, 自然语言处理, 深度学习, 人工智能

XU Delong, LIN Min, WANG Yurong, ZHANG Shujun. Survey of NLP Data Augmentation Methods Based on Large Language Models[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(6): 1395-1413.

许德龙, 林民, 王玉荣, 张树钧. 基于大语言模型的NLP数据增强方法综述[J]. 计算机科学与探索, 2025, 19(6): 1395-1413.

References

[1] ZHAO W X, ZHOU K, LI J, et al. A survey of large language models[EB/OL]. [2024-08-23]. https://arXiv.org/abs/2303.18223.
[2] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[3] MAAS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neural network acoustic models[C]//Proceedings of the 30th International Conference on Machine Learning, 2013.
[4] VASWANI A. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, 2017: 5998-6008.
[5] SCHULMAN J, ZOPH B, KIM C, et al. ChatGPT: optimizing language models for dialogue[J]. OpenAI Blog, 2022, 2(4).
[6] SHORTEN C, KHOSHGOFTAAR T M, FURHT B. Text data augmentation for deep learning[J]. Journal of Big Data, 2021, 8(1): 101.
[7] CARLINI N, ATHALYE A, PAPERNOT N, et al. On evaluating adversarial robustness[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1902.06705.
[8] 冯冉, 陈丹蕾, 化柏林. 文本数据的增强方法研究综述[J/OL]. 数据分析与知识发现 (2024-09-12)[2024-09-16]. https://kns.cnki.net/kcms/detail/10.1478.G2.20240911.1803.004.html.
FENG R, CHEN D L, HUA B L. A survey of data augmentation methods in natural language processing[J/OL]. Data Analysis and Knowledge Discovery (2024-09-12) [2024-09-16]. https://kns.cnki.net/kcms/detail/10.1478.G2.20240911.1803.004.html.
[9] 葛轶洲, 许翔, 杨锁荣, 等. 序列数据的数据增强方法综述[J]. 计算机科学与探索, 2021, 15(7): 1207-1219.
GE Y Z, XU X, YANG S R, et al. Survey on sequence data augmentation[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(7): 1207-1219.
[10] 杨锁荣, 杨洪朝, 申富饶, 等. 面向深度学习的图像数据增强综述[J]. 软件学报, 2025, 36(3): 1390-1412.
YANG S R, YANG H C, SHEN F R, et al. Image data augmentation for deep learning: a survey[J]. Journal of Software, 2025, 36(3): 1390-1412.
[11] SHORTEN C, KHOSHGOFTAAR T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data, 2019, 6(1): 60.
[12] LIU P, WANG X M, XIANG C, et al. A survey of text data augmentation[C]//Proceedings of the 2020 International Conference on Computer Communication and Network Security. Piscataway: IEEE, 2020: 191-195.
[13] FENG S Y, GANGAL V, WEI J, et al. A survey of data augmentation approaches for NLP[EB/OL]. [2024-08-23]. https://arXiv.org/abs/2105.03075.
[14] BAYER M, KAUFHOLD M A, REUTER C. A survey on data augmentation for text classification[J]. ACM Computing Surveys, 2023, 55(7): 1-39.
[15] LI B H, HOU Y T, CHE W X. Data augmentation approaches in natural language processing: a survey[J]. AI Open, 2022, 3: 71-90.
[16] WEI J, ZOU K. EDA: easy data augmentation techniques for boosting performance on text classification tasks[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1901.11196.
[17] WANG W Y, YANG D Y. That’s so annoying!!!: a lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using #petpeeve Tweets[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2015: 2557-2563.
[18] PENNINGTON J, SOCHER R, MANNING C. GloVe: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2014: 1532-1543.
[19] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1301.3781.
[20] BOJANOWSKI P, GRAVE E, JOULIN A, et al. Enriching word vectors with subword information[J]. Transactions of the Association for Computational Linguistics, 2017, 5: 135-146.
[21] WU X, LV S W, ZANG L J, et al. Conditional BERT contextual augmentation[C]//Proceedings of the 19th International Conference on Computational Science. Cham: Springer, 2019: 84-95.
[22] COULOMBE C. Text data augmentation made simple by leveraging NLP cloud APIs[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1812.04718.
[23] YU A W, DOHAN D, LUONG M T, et al. QANet: combining local convolution with global self-attention for reading comprehension[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1804.09541.
[24] HOU Y T, LIU Y J, CHE W X, et al. Sequence-to-sequence data augmentation for dialogue language understanding[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1807.01554.
[25] SUTSKEVER I. Sequence to sequence learning with neural networks[EB/OL]. [2024-08-23]. https://arXiv.org/abs/1409.3215.
[26] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[27] LONGPRE S, WANG Y, DUBOIS C. How effective is task-agnostic data augmentation for pretrained transformers? [EB/OL]. [2024-08-23]. https://arXiv.org/abs/2010.01764.
[28] RASTOGI C, MOFID N, HSIAO F I. Can we achieve more with less? Exploring data augmentation for toxic comment classification[EB/OL]. [2024-08-23]. https://arXiv.org/abs/2007.00875.
[29] YAN G, LI Y, ZHANG S, et al. Data augmentation for deep learning of judgment documents[C]//Proceedings of the 9th International Conference on Intelligence Science and Big Data Engineering. Big Data and Machine Learning. Cham: Springer, 2019: 232-242.
[30] WANG X Y, PHAM H, DAI Z H, et al. SwitchOut: an efficient data augmentation algorithm for neural machine translation[EB/OL]. [2024-09-16]. https://arXiv.org/abs/1808.07512.
[31] MIN J, MCCOY R T, DAS D, et al. Syntactic data augmentation increases robustness to inference heuristics[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2004.11999.
[32] SENNRICH R, HADDOW B, BIRCH A. Improving neural machine translation models with monolingual data[EB/OL]. [2024-09-16]. https://arXiv.org/abs/1511.06709.
[33] ANABY-TAVOR A, CARMELI B, GOLDBRAICH E, et al. Do not have enough data? Deep learning to the rescue![J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 7383-7390.
[34] DEVLIN J. BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL]. [2024-09-16]. https://arXiv.org/abs/1810.04805.
[35] YANG Y F, JIN N, LIN K, et al. Neural retrieval for question answering with cross-attention supervised data augmentation[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2009.13815.
[36] BARI M S, MOHIUDDIN T, JOTY S. UXLA: a robust unsupervised data augmentation framework for zero-resource cross-lingual NLP[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2004.13240.
[37] YOO K M, PARK D, KANG J, et al. GPT3Mix: leveraging large-scale language models for text augmentation[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2104.08826.
[38] LI Q, PENG H, LI J X, et al. A survey on text classification: from traditional to deep learning[J]. ACM Transactions on Intelligent Systems and Technology, 2022, 13(2): 1-41.
[39]WANG Z, WANG P, LIU K, et al. A comprehensive survey on data augmentation[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2405.09591.
[40] HU M Q, LIU B. Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2004: 168-177.
[41] WARSTADT A. Neural network acceptability judgments[EB/OL]. [2024-09-16]. https://arXiv.org/abs/1805.12471.
[42] VOORHEES E M. The TREC question answering track[J]. Natural Language Engineering, 2001, 7(4): 361-378.
[43] WIEBE J, WILSON T, CARDIE C. Annotating expressions of opinions and emotions in language[J]. Language Resources and Evaluation, 2005, 39(2): 165-210.
[44] LEE L, PANG B. Sentiment analysis using subjectivity summarization based on minimum cuts[C]//Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2004: 271-278.
[45] YE J J, XU N, WANG Y K, et al. LLM-DA: data augmentation via large language models for few-shot named entity recognition[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2402.14568.
[46] LI J, SUN A X, HAN J L, et al. A survey on deep learning for named entity recognition[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 50-70.
[47] FAN L, KRISHNAN D, ISOLA P, et al. Improving clip training with language rewrites[C]//Advances in Neural Information Processing Systems 36, 2023.
[48] RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 8748-8763.
[49] SAMUEL V, AYNAOU H, CHOWDHURY A G, et al. Can LLMs augment low-resource reading comprehension datasets? Opportunities and challenges[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2309.12426.
[50] ZAIB M, ZHANG W E, SHENG Q Z, et al. Conversational question answering: a survey[J]. Knowledge and Information Systems, 2022, 64(12): 3151-3195.
[51] M?LLER T, REINA A, JAYAKUMAR R, et al. COVID-QA: a question answering dataset for COVID-19[C]//Procee-dings of the 1st Workshop on NLP for COVID-19 at ACL 2020. Stroudsburg: ACL, 2020.
[52] AHMAD W U, CHI J F, TIAN Y, et al. PolicyQA: a reading comprehension dataset for privacy policies[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2010.02557.
[53] CASTELLI V, CHAKRAVARTI R, DANA S, et al. The TechQA dataset[EB/OL]. [2024-09-16]. https://arXiv.org/abs/1911.02984.
[54] ZANG Z, LUO H, WANG K, et al. Boosting unsupervised contrastive learning using diffusion-based data augmentation from scratch[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2309.07909.
[55] GUI J, CHEN T, ZHANG J, et al. A survey on self-supervised learning: algorithms, applications, and future trends[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 9052-9071.
[56] LEE N, WATTANAWONG T, KIM S, et al. LLM2LLM: boosting LLMs with novel iterative data enhancement[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2403.15042.
[57] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Image-Net classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[58] THAKUR N, REIMERS N, DAXENBERGER J, et al. Augmented SBERT: data augmentation method for improving bi-encoders for pairwise sentence scoring tasks[EB/OL]. [2024-09-16]. https://arXiv.org/abs/2010.08240.
[59] REIMERS N, GUREVYCH I. Sentence-BERT: sentence embeddings using Siamese BERT-networks[EB/OL]. [2024-09-24]. https://arXiv.org/abs/1908.10084.
[60] KUMAR V, CHOUDHARY A, CHO E. Data augmentation using pre-trained transformer models[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2003.02245.
[61] MIANA S, IVANOV R, GALLAGHER E, et al. The augmentation of large language models with random conceptual augmentation: an empirical investigation using open-source LLMs[EB/OL]. (2024-01-01) [2025-02-10]. https://www.researchgate.net.
[62] MOHAMMAD S M. Sentiment analysis: detecting valence, emotions, and other affectual states from text[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2005.11882.
[63] YU Y, ZHUANG Y, ZHANG J, et al. Large language model as attributed training data generator: a tale of diversity and bias[C]//Advances in Neural Information Processing Systems 36, 2023.
[64] TSOUMAKAS G, KATAKIS I. Multi-label classification: an overview[J]. International Journal of Data Warehousing and Mining, 2007, 3(3): 13.
[65] CHOWDHURY A G, CHADHA A. Generative data augmentation using LLMs improves distributional robustness in question answering[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2309.06358.
[66] RAJPURKAR P. Squad: 100,000+ questions for machine comprehension of text[EB/OL]. [2024-09-24]. https://arXiv.org/abs/1606.05250.
[67] CHEN X, JIANG J Y, CHANG W C, et al. MinPrompt: graph-based minimal prompt data augmentation for few-shot question answering[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2310.05007.
[68] LESTER B, AL-RFOU R, CONSTANT N, et al. The power of scale for parameter-efficient prompt tuning[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2104.08691.
[69] ZHANG Y Y, LI P F, LAI Y L, et al. Large, small or both: a novel data augmentation framework based on language models for debiasing opinion summarization[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2403.07693.
[70] SAHU G, RODRIGUEZ P, LARADJI I H, et al. Data augmentation for intent classification with off-the-shelf large language models[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2204.01959.
[71] LATIF S, USAMA M, MALIK M I, et al. Can large language models aid in annotating speech emotional data? Uncovering new frontiers[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2307.06090.
[72] YUAN J, TANG R, JIANG X, et al. LLM for patient-trial matching: privacy-aware data augmentation towards better performance and generalizability[C]//Proceedings of the American Medical Informatics Association Annual Symposium, 2023.
[73] GUO B Y, GONG Y Y, SHEN Y L, et al. GENIUS: sketch-based language model pre-training via extreme and selective masking for text generation and augmentation[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2211.10330.
[74] ZHONG Q H, LI H Y, ZHUANG L Y, et al. Iterative data generation with large language models for aspect-based sentiment analysis[EB/OL]. [2024-09-24]. https://arXiv.org/abs/2407.00341.
[75] PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. SemEval-2015 Task 12: aspect based sentiment analysis[C]//Proceedings of the 9th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2015: 486-495.
[76] PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. Semeval-2016 Task 5: aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2016: 19-30.
[77] DAI H X, LIU Z L, LIAO W X, et al. AugGPT: leveraging ChatGPT for text data augmentation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2302.13007.
[78] CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 1597-1607.
[79] CHEN Z P, ZHOU K, ZHANG B C, et al. ChatCoT: tool-augmented chain-of-thought reasoning on chat-based large language models[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2305.14323.
[80] HENDRYCKS D, BURNS C, KADAVATH S, et al. Measuring mathematical problem solving with the MATH dataset[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2103.03874.
[81] YANG Z L, QI P, ZHANG S Z, et al. HotpotQA: a dataset for diverse, explainable multi-hop question answering[EB/OL]. [2024-09-29]. https://arXiv.org/abs/1809.09600.
[82] LU H Y, LAM W. EPA: easy prompt augmentation on large language models via multiple sources and multiple targets[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2309.04725.
[83] ZHANG D, LI T, ZHANG H, et al. On data augmentation for extreme multi-label classification[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2009.10778.
[84] COSTA-JUSSà M R, CROSS J, ?ELEBI O, et al. No language left behind: scaling human-centered machine translation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2207.04672.
[85] GLIWA B, MOCHOL I, BIESEK M, et al. SAMSum corpus: a human-annotated dialogue dataset for abstractive summarization[EB/OL]. [2024-09-29]. https://arXiv.org/abs/1911.12237.
[86] GONG S S, LI M K, FENG J T, et al. DiffuSeq: sequence to sequence text generation with diffusion models[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2210.08933.
[87] BOWMAN S R, ANGELI G, POTTS C, et al. A large annotated corpus for learning natural language inference[EB/OL]. [2024-09-29]. https://arXiv.org/abs/1508.05326.
[88] POPOVI? M. chrF: character n-gram F-score for automatic MT evaluation[C]//Proceedings of the 10th Workshop on Statistical Machine Translation. Stroudsburg: ACL, 2015: 392-395.
[89] WILLIAMS A, NANGIA N, BOWMAN S R. A broad-coverage challenge corpus for sentence understanding through inference[EB/OL]. [2024-09-29]. https://arXiv.org/abs/1704. 05426.
[90] SAAKYAN A, MURESAN S. ICLEF: in-context learning with expert feedback for explainable style transfer[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2309.08583.
[91] SCHLEGEL V, LI H, WU Y P, et al. PULSAR at MEDIQA-sum 2023: large language models augmented by synthetic dialogue convert patient dialogues to medical records[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2307.02006.
[92] LI Z, SI L J, GUO C L, et al. Data augmentation for text-based person retrieval using large language models[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2405.11971.
[93] TIAN Y M, LI Y B, WANG D, et al. Enhancing CLIP-based text-person retrieval by leveraging negative samples[C]//Proceedings of the 2023 Chinese Conference on Pattern Recognition and Computer Vision. Singapore: Springer, 2023: 271-283.
[94] LI S, XIAO T, LI H S, et al. Person search with natural language description[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5187-5196.
[95] DING Z F, DING C X, SHAO Z Y, et al. Semantically self-aligned network for text-to-image part-aware person re-identification[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2107.12666.
[96] ZHU A C, WANG Z J, LI Y F, et al. DSSL: deep surroundings-person separation learning for text-based person retrieval[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York: ACM, 2021: 209-217.
[97] ZHOU J, ZHENG Y N, TANG J, et al. FlipDA: effective and robust data augmentation for few-shot learning[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2108.06332.
[98] COLIN R, NOAM S, ADAM R, et al. Exploring the limits of transfer learning with a unified text-to-text transformer[J]. Journal of Machine Learning Research, 2020, 21.
[99] WANG A, PRUKSACHATKUN Y, NANGIA N, et al. Super-GLUE: a stickier benchmark for general-purpose language understanding systems[C]//Advances in Neural Information Processing Systems 32, 2019: 3261-3275.
[100] LIU Z H, ZHU T, XIANG J X, et al. Controllable and diverse data augmentation with large language model for low-resource open-domain dialogue generation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2404.00361.
[101] LI Y R, SU H, SHEN X Y, et al. DailyDialog: a manually labelled multi-turn dialogue dataset[EB/OL]. [2024-09-29]. https://arXiv.org/abs/1710.03957.
[102] GAO J H, PI R J, LIN Y, et al. Self-guided noise-free data generation for efficient zero-shot learning[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2205.12679.
[103] YE J C, GAO J H, LI Q T, et al. ZeroGen: efficient zero-shot learning via dataset generation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2202.07922.
[104] MAAS A, DALY R E, PHAM P T, et al. Learning word vectors for sentiment analysis[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2011: 142-150.
[105] PANG B, LEE L. Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales[C]//Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics. Stroudsburg: ACL, 2005: 115-124.
[106] SOCHER R, PERELYGIN A, WU J, et al. Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2013: 1631-1642.
[107] ZHANG X, ZHAO J, LECUN Y. Character-level convolutional networks for text classification[C]//Advances in Neural Information Processing Systems 28, 2015: 649-657.
[108] UBANI S, POLAT S O, NIELSEN R. ZeroShotDataAug: generating and augmenting training data with ChatGPT[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2304.14334.
[109] LI X, ROTH D. Learning question classifiers: the role of semantic information[J]. Natural Language Engineering, 2006, 12(3): 229-249.
[110] CHENG Q Y, LI X N, LI S M, et al. Unified active retrieval for retrieval augmented generation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2406.12534.
[111] HUANG L K, HUANG J, RONG Y, et al. Frustratingly easy transferability estimation[C]//Proceedings of the 39th International Conference on Machine Learning, 2022: 9201-9225.
[112] GUNAWARDANA A, SHANI G, YOGEV S. Evaluating recommender systems[M]//Recommender systems handbook. New York: Springer US, 2012: 547-601.
[113] HOSSIN M, SULAIMAN M N. A review on evaluation metrics for data classification evaluations[J]. International Journal of Data Mining & Knowledge Management Process, 2015, 5(2): 1-11.
[114] IACUS S M, KING G, PORRO G. Causal inference without balance checking: coarsened exact matching[J]. Political Analysis, 2012, 20(1): 1-24.
[115] POWERS D M W. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2010.16061.
[116] PAPINENI K, ROUKOS S, WARD T, et al. Bleu: a method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2002: 311-318.
[117] LIN C Y. ROUGE: a package for automatic evaluation of summaries[C]//Proceedings of the 2004 Workshop on Text Summarization of ACL. Stroudsburg: ACL, 2004.
[118] DE WINTER J C F, GOSLING S D, POTTER J. Comparing the Pearson and Spearman correlation coefficients across distributions and sample sizes: a tutorial using simulations and empirical data[J]. Psychological Methods, 2016, 21(3): 273-290.
[119] KUNTZ J. Markov chains revisited[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2001.02183.
[120] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning, 2017: 1126-1135.
[121] SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]//Advances in Neural Information Processing Systems 30, 2017: 4077-4087.
[122] HOSPEDALES T, ANTONIOU A, MICAELLI P, et al. Meta-learning in neural networks: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 5149-5169.
[123] RAO S Z, HUANG J. Leveraging enhanced task embeddings for generalization in multimodal meta-learning[J]. Neural Computing and Applications, 2023, 35(15): 10765-10778.
[124] THOMAS R P, LAWRENCE A. Assessment of expert performance compared across professional domains[J]. Journal of Applied Research in Memory and Cognition, 2018, 7(2): 167-176.
[125] GHOJOGH B, NEKOEI H, GHOJOGH A, et al. Sampling algorithms, from survey sampling to Monte Carlo methods: tutorial and literature review[EB/OL]. [2024-09-29]. https://arXiv.org/abs/2011.00901.