arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.09809cs.CV
收藏

用自然语言生成反事实陈述

Generating Counterfactual Explanations with Natural Language

University of California, Berkeley(加州大学伯克利分校);University of Amsterdam(阿姆斯特丹大学)

Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata

摘要:

深度神经网络决策的自然语言解释为人工智能智能体阐明推理过程提供了一种直观的方式。当前的文本解释学习讨论图像中的类别区分特征。然而,理解哪些属性如果存在于图像中则可能改变分类决策也是有帮助的(例如,“这不是猩红唐纳雀,因为它没有黑色的翅膀。我们称这种文本解释为反事实解释,并提出了一种直观的方法来生成反事实解释,通过检查输入中缺少哪些证据,但如果存在于图像中,则可能有助于不同的分类决策。为了证明我们的方法,我们考虑一个细粒度的图像分类的任务,我们作为输入的图像和一个反事实类和输出文本,解释了为什么图像不属于反事实类。然后,我们分析我们生成的反事实的解释定性和定量使用建议的自动度量。

英文摘要:

Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to discuss class discriminative features in an image. However, it is also helpful to understand which attributes might change a classification decision if present in an image (e.g., "This is not a Scarlet Tanager because it does not have black wings.") We call such textual explanations counterfactual explanations, and propose an intuitive method to generate counterfactual explanations by inspecting which evidence in an input is missing, but might contribute to a different classification decision if present in the image. To demonstrate our method we consider a fine-grained image classification task in which we take as input an image and a counterfactual class and output text which explains why the image does not belong to a counterfactual class. We then analyze our generated counterfactual explanations both qualitatively and quantitatively using proposed automatic metrics.

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。

↑