방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 검색 증강 생성 (RAG)× | BERT 임베딩× | |
|---|---|---|
| 분야 | 텍스트 마이닝 | 텍스트 마이닝 |
| 계열 | Process / pipeline | Process / pipeline |
| 기원 연도≠ | 2020 | 2019 |
| 창시자≠ | Lewis, Patrick et al. (Meta AI / Facebook AI Research) | Devlin, Chang, Lee & Toutanova (Google AI) |
| 유형≠ | Hybrid retrieval + generation pipeline | Contextual transformer text-representation method |
| 원전≠ | Lewis, P. et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS), 33, 9459-9474. DOI ↗ | 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≠ | RAG, retrieval-augmented LLM, grounded generation, Erişim Destekli Metin Üretimi (RAG) | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri |
| 관련≠ | 7 | 4 |
| 요약≠ | Retrieval-Augmented Generation (RAG) is a natural-language-processing pipeline introduced by Lewis et al. in 2020 that strengthens a large language model (LLM) with evidence fetched at inference time from an external knowledge base. Instead of relying solely on what a model memorised during training, RAG first retrieves the most relevant passages from a document index and then hands those passages to the LLM as context, grounding the generated answer in verifiable, up-to-date information. The approach reduces hallucination and allows domain-specific or time-sensitive knowledge to be injected without retraining the model. | 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 ↗ |
|
|