Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.
@article{arxiv.2005.00432,
title = {Topological Sort for Sentence Ordering},
author = {Shrimai Prabhumoye and Ruslan Salakhutdinov and Alan W Black},
journal= {arXiv preprint arXiv:2005.00432},
year = {2020}
}
Comments
Will be published at the Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL) 2020