Topological Sort for Sentence Ordering
This work addresses the problem of document coherence for natural language processing applications, but it is incremental as it builds on existing sentence ordering tasks.
The authors tackled sentence ordering by reframing it as a constraint solving problem rather than sequence prediction, and their new technique improved coherence in documents across four datasets, as shown by better results on automatic and human metrics.
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.