Comparer des méthodes

	Adaptation de domaine pour la résumé de texte	Résumé de texte affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2019–2021	2019–2020
Auteur d'origine	Multiple contributors; domain adaptation methods consolidated via transformer-era NLP (c. 2019–2021)	Lewis et al. (BART); Zhang et al. (PEGASUS); Raffel et al. (T5)
Type	Domain adaptation of sequence-to-sequence neural summarization	Fine-tuned sequence-to-sequence neural model
Source fondatrice	Fabbri, A. R., KryŜiński, W., McCann, B., Xiong, C., Socher, R., & Radev, D. (2021). SummEval: Re-evaluating Summarization Evaluation. Transactions of the Association for Computational Linguistics, 9, 391–409.	Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2020). PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. Proceedings of the 37th International Conference on Machine Learning (ICML), 119, 11328–11339.
Alias	domain-adapted summarization, domain-specific summarization, cross-domain summarization, DA-summarization	Fine-tuned summarization model, Abstractive summarization via fine-tuning, Seq2Seq fine-tuning for summarization, BART/T5/PEGASUS fine-tuning
Apparentées	6	5
Résumé	Domain-adaptive text summarization fine-tunes or adapts a pre-trained sequence-to-sequence language model on a target domain corpus so that summaries conform to domain-specific vocabulary, style, and factual constraints. It bridges the gap between general-purpose summarization models trained on news or web data and specialized domains such as biomedical literature, legal documents, scientific papers, or financial reports.	Fine-Tuned Text Summarization adapts a large pre-trained sequence-to-sequence model — such as BART, T5, or PEGASUS — to generate concise summaries of documents by training on domain-specific (document, summary) pairs. The approach yields substantially more fluent and faithful summaries than extractive or generic approaches by leveraging knowledge encoded in billions of pre-training tokens.