方法对比

	可解释的非负矩阵分解主题模型	可解释的BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2001 (NMF); XAI integration ~2017–present	2019–2020
提出者	Lee, D. D. & Seung, H. S. (NMF); XAI layer attributed to community practice post-2016	Devlin et al. (BERT); explainability methods by Lundberg & Lee (SHAP), Ribeiro et al. (LIME), Sundararajan et al. (Integrated Gradients)
类型	Interpretable unsupervised topic model	Pre-trained transformer classifier with post-hoc or intrinsic explainability
开创性文献	Lee, D. D., & Seung, H. S. (2001). Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 13, 556–562.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186.
别名	XAI-NMF, interpretable NMF topic model, explainable NMF, transparent NMF topic modeling	XAI-BERT, interpretable BERT classifier, BERT with post-hoc explanation, transparent BERT classification
相关	6	6
摘要	An 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.	Explainable BERT-based Classification combines the predictive power of fine-tuned BERT transformers for text classification with post-hoc or intrinsic explainability techniques — such as SHAP, LIME, attention analysis, or integrated gradients — to reveal which words or tokens drove each prediction. The result is a classifier that is both accurate and interpretable enough for high-stakes or auditable NLP applications.