เปรียบเทียบวิธี

	Domain-adaptive Doc2Vec	การจำแนกประเภทแบบ BERT ที่ปรับให้เข้ากับโดเมน
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning
ปีกำเนิด	2014 (Doc2Vec); domain-adaptive application mid-2010s onward	2019–2020
ผู้ริเริ่ม	Le & Mikolov (Doc2Vec); domain adaptation literature (Blitzer, Daumé III, and others)	Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT
ประเภท	Unsupervised / domain-adaptive document embedding	Domain-adaptive pre-training followed by supervised fine-tuning
แหล่งต้นตำรับ	Le, Q. V., & Mikolov, T. (2014). Distributed representations of sentences and documents. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), PMLR 32(2), 1188–1196.	Gururangan, S., Marasovic, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 8342–8360.
ชื่อเรียกอื่น	domain-adapted Doc2Vec, cross-domain paragraph vector, domain-adaptive PV-DM, domain-adaptive PV-DBOW	DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT
ที่เกี่ยวข้อง	5	6
สรุป	Domain-adaptive Doc2Vec adapts the Paragraph Vector (Doc2Vec) framework so that document embeddings learned on a source domain transfer effectively to a target domain. By aligning the representation space across domains during or after training, the model produces embeddings that are informative on both, enabling cross-domain classification, sentiment analysis, and retrieval with limited target-domain labels.	Domain-adaptive BERT-based classification extends the standard fine-tuning pipeline by first continuing BERT's masked-language-model pre-training on a large corpus of in-domain unlabeled text, then fine-tuning the adapted model on labeled examples for the target classification task. This two-stage approach closes the vocabulary and distributional gap between BERT's general pre-training corpus and specialized domains such as biomedicine, law, finance, or social-media text.