行为探究：基于行为反事实的行为解释
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
摘要：
越来越多的工作利用探测来研究神经模型的工作，通常被认为是黑箱。最近，围绕探测范式的局限性出现了一场持续的辩论。在这项工作中，我们指出无法从探测结果中推断出行为结论，并提供了一种替代方法，该方法侧重于如何使用信息，而不是编码什么信息。我们的方法，直觉探测，遵循的直觉，一个属性的效用为一个给定的任务，可以通过测量的因果干预，将其从代表性的影响进行评估。有了这个新的分析工具，我们可以提出以前不可能提出的问题，例如，词性信息对单词预测重要吗？我们对BERT进行了一系列的分析来回答这些类型的问题。我们的研究结果表明，传统的探测性能是不相关的任务的重要性，我们呼吁增加审查的索赔，从探测结果得出行为或因果关系的结论。
英文摘要：
A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the inability to infer behavioral conclusions from probing results and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded. Our method, Amnesic Probing, follows the intuition that the utility of a property for a given task can be assessed by measuring the influence of a causal intervention that removes it from the representation. Equipped with this new analysis tool, we can ask questions that were not possible before, e.g. is part-of-speech information important for word prediction? We perform a series of analyses on BERT to answer these types of questions. Our findings demonstrate that conventional probing performance is not correlated to task importance, and we call for increased scrutiny of claims that draw behavioral or causal conclusions from probing results.
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。
