方法对比

	可解释句子嵌入	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	2016–2018	2019–2020
提出者	Conneau et al.; Ribeiro et al. (probing + LIME frameworks)	Devlin et al. (BERT); explainability methods by Lundberg & Lee (SHAP), Ribeiro et al. (LIME), Sundararajan et al. (Integrated Gradients)
类型	Post-hoc interpretability applied to sentence encoders	Pre-trained transformer classifier with post-hoc or intrinsic explainability
开创性文献	Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018). What you can cram into a single $\vec{v}$ector: Probing sentence embeddings for linguistic properties. In Proceedings of ACL 2018, pp. 2126–2136.	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	interpretable sentence representations, XAI sentence embeddings, probing sentence embeddings, explainable sentence vectors	XAI-BERT, interpretable BERT classifier, BERT with post-hoc explanation, transparent BERT classification
相关	6	6
摘要	Explainable sentence embeddings combine dense sentence representation learning with post-hoc or intrinsic interpretability tools — such as probing classifiers, LIME, SHAP, or attention attribution — to reveal what linguistic and semantic information is encoded in a sentence vector and why a downstream model makes a given prediction. The goal is to retain the representational power of modern encoders while making their behavior auditable.	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.