提出无需模型内部知识的可解释性方法，精准定位文本决策关键词。
MASE: Interpretable NLP Models via Model-Agnostic Saliency Estimation
- 用嵌入层的归一化高斯扰动估计词重要性，不依赖模型结构。
- 在多个数据集上比现有方法提升3.2%~5.7%的判别准确率差异。
- 适合需要快速理解大模型决策逻辑的研究者和开发者。
深度神经网络在自然语言处理领域取得显著进展，但其可解释性仍面临挑战，尤其在评估复杂决策过程时。传统方法多依赖事后解释，如显著性图或特征可视化，难以适配NLP中离散的词数据。为此，本文提出模型无关的显著性估计（MASE）框架，可在无需了解模型内部结构的情况下，为文本预测模型提供局部解释。MASE通过在嵌入层施加归一化线性高斯扰动（NLGP），而非原始词输入，高效估计输入显著性。实验表明，相比其他模型无关解释方法，MASE在Delta Accuracy指标上表现更优，展现出作为揭示文本模型运作机制的有力工具潜力。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) have made significant strides in Natural Language Processing (NLP), yet their interpretability remains elusive, particularly when evaluating their intricate decision-making processes. Traditional methods often rely on post-hoc interpretations, such as saliency maps or feature visualization, which might not be directly applicable to the discrete nature of word data in NLP. Addressing this, we introduce the Model-agnostic Saliency Estimation (MASE) framework. MASE offers local explanations for text-based predictive models without necessitating in-depth knowledge of a model's internal architecture. By leveraging Normalized Linear Gaussian Perturbations (NLGP) on the embedding layer instead of raw word inputs, MASE efficiently estimates input saliency. Our results indicate MASE's superiority over other model-agnostic interpretation methods, especially in terms of Delta Accuracy, positioning it as a promising tool for elucidating the operations of text-based models in NLP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。