GPT

GPT is a Transformer-based architecture and training procedure for natural language processing tasks. Training follows a two-stage procedure. First, a language modeling objective is used on the unlabeled data to learn the initial parameters of a neural network model. Subsequently, these parameters are adapted to a target task using the corresponding supervised objective.
相关学科: GPT-2ELMoGPT-3BERTXLNetRoBERTaT5GPT-NeoULMFiTLabel Smoothing

学科讨论

讨论Icon

暂无讨论内容,你可以

推荐文献

按被引用数

学科管理组

暂无学科课代表,你可以申请成为课代表

重要学者

Ilya Sutskever

165856 被引用,113 篇论文

Christopher D. Manning

123173 被引用,515 篇论文

Alexander J. Smola

89395 被引用,459 篇论文

Elhanan Helpman

69817 被引用,430 篇论文

Alexey Svyatkovskiy

56905 被引用,739 篇论文

Pieter Abbeel

52831 被引用,627 篇论文

Kazuaki Chayama

48707 被引用,1783 篇论文

Edgar Erdfelder

46910 被引用,178 篇论文

John Shawe-Taylor

41627 被引用,580 篇论文

Bronwyn H. Hall

38558 被引用,378 篇论文