This Reads Like That：面向可解释自然语言处理的深度学习
This Reads Like That: Deep Learning for Interpretable Natural Language Processing
- ETH Zürich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究将原型网络拓展至自然语言处理领域，提出可学习加权相似性度量和事后可解释机制，在多个数据集上提升了预测性能与解释忠实度。
AI中文摘要：
原型学习是一种专为固有可解释决策设计的主流机器学习方法，它利用与已学习原型的相似性对新数据进行分类。该方法目前主要应用于计算机视觉领域，本文在已有研究基础上，进一步探索原型网络向自然语言处理领域的拓展。我们提出了一种可学习的加权相似性度量方法，通过聚焦预训练句子嵌入的信息维度来优化相似性计算。此外，我们还提出了一种事后可解释性机制，能够从原型和输入句子中提取与预测相关的词汇。最后，实验结果表明，与此前基于原型的方法相比，本文提出的方法不仅在AG News和RT Polarity数据集上提升了预测性能，而且与基于理据的循环卷积方法相比，还提升了解释的忠实度。
英文摘要：
Prototype learning, a popular machine learning method designed for inherently interpretable decisions, leverages similarities to learned prototypes for classifying new data. While it is mainly applied in computer vision, in this work, we build upon prior research and further explore the extension of prototypical networks to natural language processing. We introduce a learned weighted similarity measure that enhances the similarity computation by focusing on informative dimensions of pre-trained sentence embeddings. Additionally, we propose a post-hoc explainability mechanism that extracts prediction-relevant words from both the prototype and input sentences. Finally, we empirically demonstrate that our proposed method not only improves predictive performance on the AG News and RT Polarity datasets over a previous prototype-based approach, but also improves the faithfulness of explanations compared to rationale-based recurrent convolutions.
