We present an attention-based ranking framework for learning to order sentences given a paragraph. Our framework is built on a bidirectional sentence encoder and a self-attention based transformer network to obtain an input order invariant representation of paragraphs. Moreover, it allows seamless training using a variety of ranking based loss functions, such as pointwise, pairwise, and listwise ranking. We apply our framework on two tasks: Sentence Ordering and Order Discrimination. Our framework outperforms various state-of-the-art methods on these tasks on a variety of evaluation metrics. We also show that it achieves better results when using pairwise and listwise ranking losses, rather than the pointwise ranking loss, which suggests that incorporating relative positions of two or more sentences in the loss function contributes to better learning.

本论文提出了一个基于注意力机制的排序框架，旨在训练模型进行句子排序和辨别任务。该框架采用双向句子编码器和自注意力变换网络以获取与输入顺序无关的段落表示。同时，它能够使用各种基于排序的损失函数进行无缝训练，并在两个任务中应用。实验结果表明，该框架在多个评估指标上优于众多最先进的方法。同时，相对于点对排序损失函数，该框架在使用点对和列表排序损失函数时取得更好的结果，这表明将两个或多个句子的相对位置纳入损失函数有利于更好的学习。

基于注意力机制的深度排序网络用于句子排序学习