“你会找到这些捷径吗？”“A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification
"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification
摘要：
特征属性将重要性分数分配给特征的输入显著性方法是丰富的，但是对于相同输入的相同模型可能产生令人惊讶的不同结果。虽然如果假设不同的重要性定义，预计会有差异，但大多数方法都声称提供忠实的属性，并指出与模型预测最相关的特征。现有的工作对忠诚度的评价是不确定的，并没有提供一个明确的答案，如何不同的方法进行比较。专注于文本分类和模型调试的情况下，我们的主要贡献是一个协议的忠实性评估，利用部分合成数据，以获得地面真相的特征重要性排名。根据协议，我们对BERT和LSTM模型的一系列数据集和快捷方式上的四个标准显着性方法类进行了深入分析，并证明了一些最流行的方法配置即使对于最简单的快捷方式也提供了较差的结果。我们建议遵循每个新任务和模型组合的协议，以找到识别快捷方式的最佳方法。
英文摘要：
Feature attribution a.k.a. input salience methods which assign an importance score to a feature are abundant but may produce surprisingly different results for the same model on the same input. While differences are expected if disparate definitions of importance are assumed, most methods claim to provide faithful attributions and point at the features most relevant for a model's prediction. Existing work on faithfulness evaluation is not conclusive and does not provide a clear answer as to how different methods are to be compared. Focusing on text classification and the model debugging scenario, our main contribution is a protocol for faithfulness evaluation that makes use of partially synthetic data to obtain ground truth for feature importance ranking. Following the protocol, we do an in-depth analysis of four standard salience method classes on a range of datasets and shortcuts for BERT and LSTM models and demonstrate that some of the most popular method configurations provide poor results even for simplest shortcuts. We recommend following the protocol for each new task and model combination to find the best method for identifying shortcuts.
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。
