ScholarGate
어시스턴트

방법 비교

선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.

설명 가능한 NMF 토픽 모델×NMF 토픽 모델×
분야딥러닝딥러닝
계열Machine learningMachine learning
기원 연도2001 (NMF); XAI integration ~2017–present1999
창시자Lee, D. D. & Seung, H. S. (NMF); XAI layer attributed to community practice post-2016Lee, D. D. & Seung, H. S.
유형Interpretable unsupervised topic modelMatrix factorization / unsupervised topic model
원전Lee, D. D., & Seung, H. S. (2001). Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 13, 556–562. link ↗Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. DOI ↗
별칭XAI-NMF, interpretable NMF topic model, explainable NMF, transparent NMF topic modelingNMF, Non-negative Matrix Factorization, NMF for Topic Modeling, NNMF Topic Model
관련64
요약An Explainable NMF Topic Model combines Non-negative Matrix Factorization — a parts-based decomposition of a document-term matrix — with explicit interpretability techniques such as coherence metrics, word contribution scores, and SHAP-style attribution to make discovered topics transparent and auditable by human readers.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
  1. v1
  2. 2 출처
  3. PUBLISHED
  1. v1
  2. 2 출처
  3. PUBLISHED

검색으로 이동 슬라이드 다운로드

ScholarGate방법 비교: Explainable NMF Topic Model · NMF Topic Model. 2026-06-15에 다음에서 검색함: https://scholargate.app/ko/compare