방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 미세조정된 문장 임베딩× | 파인튜닝 트랜스포머× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2019 | 2017–2019 |
| 창시자≠ | Reimers, N. & Gurevych, I. | Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al. |
| 유형≠ | Supervised / contrastive fine-tuning of pre-trained sentence encoders | Transfer learning / supervised fine-tuning |
| 원전≠ | Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3982–3992. DOI ↗ | Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. link ↗ |
| 별칭 | SBERT fine-tuning, sentence transformer fine-tuning, domain-adapted sentence embeddings, fine-tuned sentence encoders | Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer |
| 관련≠ | 5 | 4 |
| 요약≠ | Fine-Tuned Sentence Embeddings adapt a general-purpose pre-trained sentence encoder — such as Sentence-BERT — to a specific domain or task by continuing training on labeled or paired text data from that domain. The resulting embeddings capture domain-specific semantic structure far better than off-the-shelf vectors, improving downstream tasks such as semantic similarity, clustering, classification, and retrieval. | Fine-tuning a Transformer adapts a large pre-trained model — such as BERT, GPT, or ViT — to a specific downstream task by continuing gradient-based training on a labelled target dataset. This two-stage paradigm (pre-train then fine-tune) consistently achieves state-of-the-art results across NLP and computer vision tasks with far less task-specific data than training from scratch. |
| ScholarGate데이터셋 ↗ |
|
|