论文标题
健忘症探测：具有失忆症反事实的行为解释
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
论文作者
论文摘要
越来越多的工作利用探测来研究神经模型的工作，通常被认为是黑匣子。最近，围绕探测范式的局限性出现了持续的辩论。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，而不是编码哪些信息。我们的方法是失忆探测，遵循以下直觉，即可以通过测量因果干预的影响来评估特定任务的财产效用，从而将其从表示形式中删除。配备了这个新的分析工具，我们可以提出以前无法的问题，例如语音信息的一部分对于单词预测很重要吗？我们对BERT进行了一系列分析，以回答这些类型的问题。我们的发现表明，常规探测性能与任务重要性无关，我们呼吁对从探测结果得出行为或因果关系的主张进行更多的审查。
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.
