방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| NLP를 위한 대조 학습× | BERT 임베딩× | |
|---|---|---|
| 분야 | 텍스트 마이닝 | 텍스트 마이닝 |
| 계열 | Process / pipeline | Process / pipeline |
| 기원 연도≠ | 2020–2021 | 2019 |
| 창시자≠ | Gao, Yao & Chen (SimCSE, 2021); Khosla et al. (Supervised Contrastive, 2020) | Devlin, Chang, Lee & Toutanova (Google AI) |
| 유형≠ | Self-supervised / supervised representation learning | Contextual transformer text-representation method |
| 원전≠ | Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of EMNLP 2021. link ↗ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186. DOI ↗ |
| 별칭≠ | SimCSE, contrastive sentence embeddings, ContrastiveBERT, Karşıtlık Öğrenmesi — NLP (Contrastive Learning) | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri |
| 관련 | 4 | 4 |
| 요약≠ | Contrastive learning for NLP is a representation-learning technique — popularised by SimCSE (Gao et al., 2021) and Supervised Contrastive Learning (Khosla et al., 2020) — that trains a text encoder by pulling embeddings of similar text pairs together while pushing embeddings of dissimilar pairs apart. The result is a dense, high-quality embedding space that can be learned with no labels at all, or with minimal supervision, making it especially valuable when annotated data are scarce. | BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA. |
| ScholarGate데이터셋 ↗ |
|
|