arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.07550cs.CL
收藏

神经理性模型的不合理性

The Irrationality of Neural Rationale Models

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

Yiming Zheng, Serena Booth, Julie Shah, Yilun Zhou

摘要:

神经基本原理模型在NLP任务的可解释预测中很受欢迎。在这些中,选择器提取输入文本的片段,称为基本原理,并将这些片段传递给分类器进行预测。由于基本原理是分类器可访问的唯一信息,因此可以将其定义为解释。这样的描述是绝对正确的吗?在本文中,我们认为相反,哲学观点和经验证据表明,理性模型,也许,比预期的更合理和可解释的。我们呼吁对这些模型进行更严格和全面的评估,以确保确实实现了所需的可解释性。代码可以在https://github.com/yimingz89/Neural-Rationale-Analysis上找到。

英文摘要:

Neural rationale models are popular for interpretable predictions of NLP tasks. In these, a selector extracts segments of the input text, called rationales, and passes these segments to a classifier for prediction. Since the rationale is the only information accessible to the classifier, it is plausibly defined as the explanation. Is such a characterization unconditionally correct? In this paper, we argue to the contrary, with both philosophical perspectives and empirical evidence suggesting that rationale models are, perhaps, less rational and interpretable than expected. We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved. The code can be found at https://github.com/yimingz89/Neural-Rationale-Analysis.

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。

↑