剪枝文字以实现词级高效可解释性
Pruning Literals for Highly Efficient Explainability at Word Level
AI总结：
本文提出一种事后子句剪枝方法，移除Tsetlin机中随机放置的文字，以提升词级可解释性；在YELP-HAT数据集上，剪枝后的模型注意力图更接近人类，且准确性提升4%-9%。
摘要：
设计可解释模型对于自然语言处理（NLP）如今变得至关重要，因为大多数最先进的机器学习模型对其预测提供的解释有限。在可解释模型的谱系中，Tsetlin机（TM）因其能够使用命题逻辑提供词级解释而颇具前景。然而，尽管其学习过程透明，但子句中文字（命题逻辑）的复杂组合使得模型难以被人类理解，这引发了担忧。在本文中，我们设计了一种事后子句剪枝方法，消除子句中随机放置的文字，从而使模型比原始TM更高效地可解释。在公开的YELP-HAT数据集上的实验表明，所提出的剪枝TM的注意力图比原始TM的注意力图更接近人类注意力图。此外，成对相似性度量也超越了基于注意力图的神经网络模型。在准确性方面，所提出的剪枝方法并未显著降低准确性，反而在某些测试数据上将性能提升了4%至9%。
英文摘要：
Designing an explainable model becomes crucial now for Natural Language Processing(NLP) since most of the state-of-the-art machine learning models provide a limited explanation for the prediction. In the spectrum of an explainable model, Tsetlin Machine(TM) is promising because of its capability of providing word-level explanation using proposition logic. However, concern rises over the elaborated combination of literals (propositional logic) in the clause that makes the model difficult for humans to comprehend, despite having a transparent learning process. In this paper, we design a post-hoc pruning of clauses that eliminate the randomly placed literals in the clause thereby making the model more efficiently interpretable than the vanilla TM. Experiments on the publicly available YELP-HAT Dataset demonstrate that the proposed pruned TM's attention map aligns more with the human attention map than the vanilla TM's attention map. In addition, the pairwise similarity measure also surpasses the attention map-based neural network models. In terms of accuracy, the proposed pruning method does not degrade the accuracy significantly but rather enhances the performance up to 4% to 9% in some test data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
