While Transformer language models (LMs) are state-of-the-art for information extraction, long text introduces computational challenges requiring suboptimal preprocessing steps or alternative model architectures. Sparse attention LMs can represent longer sequences, overcoming performance hurdles. However, it remains unclear how to explain predictions from these models, as not all tokens attend to each other in the self-attention layers, and long sequences pose computational challenges for explainability algorithms when runtime depends on document length. These challenges are severe in the medical context where documents can be very long, and machine learning (ML) models must be auditable and trustworthy. We introduce a novel Masked Sampling Procedure (MSP) to identify the text blocks that contribute to a prediction, apply MSP in the context of predicting diagnoses from medical text, and validate our approach with a blind review by two clinicians. Our method identifies about 1.7x more clinically informative text blocks than the previous state-of-the-art, runs up to 100x faster, and is tractable for generating important phrase pairs. MSP is particularly well-suited to long LMs but can be applied to any text classifier. We provide a general implementation of MSP.
翻译:虽然变换语言模型(LMS)是信息提取的最先进,但长文本带来了计算挑战,需要低于最优化的预处理步骤或替代模型结构。粗略的注意LMS可以代表较长的顺序,克服性能障碍。然而,仍然不清楚如何解释这些模型的预测,因为自我注意层中并非所有象征都互相关注,长序列对运行时的可解释性算法构成计算挑战取决于文件长度。这些挑战在医学方面是严峻的,因为文件可以很长,而机器学习(ML)模型必须是可审计和可信赖的。我们引入了一部新颖的蒙面抽样取样程序(MSP),以确定有助于预测的文本块,在预测医学文本诊断时应用MSP,并通过两名临床医生的盲目审查来验证我们的方法。我们的方法确定了比先前的状态更能提供临床信息的文本块约1.7x,速度要快到100x,并且可用于生成重要的词组。MSP系统特别适合长期的LMS。我们可以提供常规文本。