Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents. In this paper we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-and-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-to-end training technique for Select-and-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick. We conduct extensive experiments to demonstrate that our approach is competitive to state-of-the-art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design. Finally, we present real-world applications that benefit from our sentence selection method.
翻译:但由于培训前任务对语言的理解程度较高,神经文件排名模型的成绩令人印象深刻。然而,由于这些模型(通常以变压器为基础的模型)的复杂性和参数数量众多,这些模型往往无法解释,因为排名决定不能明确归因于投入文件的具体部分。在本文件中,我们提出了本可解释的排序模型,作为预测决定的副产品。我们引入了文件排名选择和兰克模型,我们首先在文件中作为一组选定句子提出解释。随后,我们仅仅使用解释或选择来作出预测,在排名过程中作出一等公民的解释。从技术上讲,我们把选择判决视为与最后产出的排位共同培训的潜在变量。为此,我们提议了选择和兰克模型的端到端培训技术,利用古姆贝尔峰峰法进行可重新计量的子取样。我们进行了广泛的实验,以证明我们的方法对州级方法具有竞争力。我们的方法广泛适用于众多的排名任务,从最后的排序中可以解释我们的目标选择方法。