方法对比

	T5（Text-to-Text Transfer Transformer）	迁移学习
领域	深度学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2020	2010 (formalized); 1990s (early roots)
提出者	Raffel, C.; Shazeer, N.; Roberts, A.; et al. (Google Brain)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
类型	Pre-trained encoder-decoder Transformer (sequence-to-sequence)	Learning paradigm
开创性文献	Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, 21(140), 1–67.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
别名	T5, Text-to-Text Transfer Transformer, T5-Small, T5-Base	TL, domain adaptation, fine-tuning, pre-trained model adaptation
相关	2	3
摘要	T5 is a unified sequence-to-sequence deep learning framework introduced by Raffel et al. at Google Brain in 2020, published in the Journal of Machine Learning Research (Vol. 21, No. 140). It reframes every NLP task — classification, translation, summarisation, question answering, and more — as a text-to-text problem: both input and output are always character strings, enabling a single encoder-decoder Transformer to be pre-trained once and fine-tuned across tasks with a consistent interface. T5 introduced span-corruption pre-training and the C4 corpus, and its largest variant (11B parameters) achieved state-of-the-art results across a wide range of NLP benchmarks at the time of publication.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.