Deep Attentive Ranking Networks for Learning to Order Sentences
This work addresses sentence ordering for natural language processing applications, representing an incremental improvement over existing methods.
The authors tackled the problem of ordering sentences in paragraphs by developing an attention-based ranking framework that uses bidirectional sentence encoding and transformer networks to create order-invariant representations. Their framework outperformed state-of-the-art methods on Sentence Ordering and Order Discrimination tasks, achieving better results with pairwise and listwise ranking losses compared to pointwise losses.
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.