Comparer des méthodes

	Génération de Langage Naturel	Ajustement fin de GPT
Domaine	Fouille de textes	Apprentissage profond
Famille	Process / pipeline	Machine learning
Année d'origine	1970s (rule-based origins); 2000s (probabilistic); 2017+ (neural/transformer era)	2019
Auteur d'origine	Reiter & Dale (classical pipeline, 2000); Gatt & Krahmer (modern survey, 2018)	Radford, A. et al. (OpenAI)
Type	NLP generative task — structured data to natural language	Fine-tuning of pretrained autoregressive language models
Source fondatrice	Gatt, A. & Krahmer, E. (2018). Survey of the State of the Art in Natural Language Generation: Core Tasks, Applications and Evaluation. Journal of Artificial Intelligence Research, 61, 65-170.	Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. & Sutskever, I. (2019). Language Models are Unsupervised Multitask Learners. OpenAI Technical Report.
Alias	NLG, data-to-text, text generation, Doğal Dil Üretimi (NLG)	GPT İnce Ayar ve Talimat Uyarlaması, GPT fine-tuning, instruction tuning, LLM fine-tuning
Apparentées	7	5
Résumé	Natural Language Generation (NLG) is the branch of natural language processing that automatically produces fluent, human-readable text from structured data, knowledge graphs, or semantic representations. Formalised in the classical pipeline by Reiter and Dale (2000) and surveyed comprehensively by Gatt and Krahmer (2018), NLG powers applications ranging from automated financial reporting and weather bulletins to data storytelling and conversational agents.	GPT fine-tuning adapts pretrained autoregressive language models such as GPT-2/3/4 or LLaMA — introduced in OpenAI's 2019 work by Radford and colleagues — to domain-specific data or to instruction following via reinforcement learning from human feedback (RLHF) or DPO. It is used for instruction following, domain adaptation, and generative tasks.