BERT4SO: Neural Sentence Ordering by Fine-tuning BERT [article]

Yutao Zhu, Jian-Yun Nie, Kun Zhou, Shengchao Liu, Yabo Ling, Pan Du
<span title="2021-05-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Sentence ordering aims to arrange the sentences of a given text in the correct order. Recent work frames it as a ranking problem and applies deep neural networks to it. In this work, we propose a new method, named BERT4SO, by fine-tuning BERT for sentence ordering. We concatenate all sentences and compute their representations by using multiple special tokens and carefully designed segment (interval) embeddings. The tokens across multiple sentences can attend to each other which greatly
more &raquo; ... their interactions. We also propose a margin-based listwise ranking loss based on ListMLE to facilitate the optimization process. Experimental results on five benchmark datasets demonstrate the effectiveness of our proposed method.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="">arXiv:2103.13584v3</a> <a target="_blank" rel="external noopener" href="">fatcat:o2hgpwecanhwncmq5bt7vw6uzu</a> </span>
<a target="_blank" rel="noopener" href="" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="" title=" access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> </button> </a>