방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 미세 조정 토픽 모델링× | NMF 토픽 모델× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2020–2022 | 1999 |
| 창시자≠ | Bianchi et al.; Grootendorst, M. | Lee, D. D. & Seung, H. S. |
| 유형≠ | Fine-tuned neural topic model | Matrix factorization / unsupervised topic model |
| 원전≠ | Bianchi, F., Terragni, S., Hovy, D., Nozza, D., & Fersini, E. (2021). Cross-lingual Contextualized Topic Models with Zero-shot Learning. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 1676–1683. DOI ↗ | Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. DOI ↗ |
| 별칭 | neural topic modeling, fine-tuned topic model, pre-trained topic model, contextual topic modeling | NMF, Non-negative Matrix Factorization, NMF for Topic Modeling, NNMF Topic Model |
| 관련≠ | 6 | 4 |
| 요약≠ | Fine-Tuned Topic Modeling adapts pre-trained language models — such as BERT or Sentence-BERT — to discover latent topics in document collections. Unlike classical probabilistic methods (LDA, NMF), it leverages rich contextual embeddings and optionally fine-tunes the backbone on domain-specific corpora, producing more coherent and semantically meaningful topics, especially on short texts or specialized domains. | Non-negative Matrix Factorization (NMF) is an unsupervised matrix decomposition method that discovers latent topics in a text corpus by factoring a document-term matrix into two non-negative matrices — one encoding topic-word weights, the other document-topic weights. The non-negativity constraint yields parts-based, additive representations that tend to produce clean, interpretable topics. |
| ScholarGate데이터셋 ↗ |
|
|