通过原型学习实现文本分类的细粒度可解释性
Advancing Interpretability in Text Classification through Prototype Learning
- 基于原型的跨度提取与语义对齐机制
- 在多个基准上超越可解释与非可解释模型
- 适合需要透明决策过程的文本分析场景
深度神经网络在各类文本任务中取得了显著性能，但往往缺乏可解释性，限制了其在需要透明性的应用场景中的使用。为此，我们提出ProtoLens，一种新型原型驱动模型，可提供细粒度、子句级的文本分类可解释性。ProtoLens采用原型感知跨度提取模块，识别与学习到的原型相关的文本片段，并通过原型对齐机制确保原型在训练过程中始终保持语义合理性。通过将原型嵌入与人类可理解的示例对齐，ProtoLens在保持竞争性准确率的同时提供可解释的预测结果。大量实验表明，ProtoLens在多个文本分类基准上优于基于原型及不可解释的基线模型。代码与数据已公开于https://anonymous.4open.science/r/ProtoLens-CE0B/。
原文摘要 · Abstract (English)
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel prototype-based model that provides fine-grained, sub-sentence level interpretability for text classification. ProtoLens uses a Prototype-aware Span Extraction module to identify relevant text spans associated with learned prototypes and a Prototype Alignment mechanism to ensure prototypes are semantically meaningful throughout training. By aligning the prototype embeddings with human-understandable examples, ProtoLens provides interpretable predictions while maintaining competitive accuracy. Extensive experiments demonstrate that ProtoLens outperforms both prototype-based and non-interpretable baselines on multiple text classification benchmarks. Code and data are available at \url{https://anonymous.4open.science/r/ProtoLens-CE0B/}.
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。