방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 미세 조정 LDA 토픽 모델× | 문장 임베딩× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2003 (base); adaptation practice ~2010s | 2015–2019 |
| 창시자≠ | Blei, D. M., Ng, A. Y., & Jordan, M. I. (base LDA); domain adaptation via online/warm-start LDA | Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019) |
| 유형≠ | Probabilistic generative topic model (fine-tuned / domain-adapted) | Representation learning / embedding |
| 원전≠ | Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022. link ↗ | 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), 3980–3990. DOI ↗ |
| 별칭 | Domain-Adapted LDA, Adapted LDA, LDA Fine-Tuning, Online LDA Fine-Tuning | sentence vectors, sentence representations, SBERT, semantic sentence encoding |
| 관련≠ | 5 | 4 |
| 요약≠ | Fine-Tuned LDA adapts a Latent Dirichlet Allocation model trained on a large general corpus to a specific target domain by continuing inference on domain-specific documents. Rather than fitting LDA from scratch, the pre-trained topic-word distributions are used as an informed starting point, enabling the model to discover coherent domain topics faster and with less data than training cold. | Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines. |
| ScholarGate데이터셋 ↗ |
|
|