Neural Sentence Ordering
This work addresses sentence ordering for natural language generation applications, but it is incremental as it focuses on isolating the task rather than introducing a novel method.
The authors tackled the problem of sentence ordering as an isolated task, rather than as part of a downstream application, and validated their data-driven approach with extensive experiments on a large corpus of academic texts.
Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its importance, we propose to study it as an isolated task. We collect a large corpus of academic texts, and derive a data driven approach to learn pairwise ordering of sentences, and validate the efficacy with extensive experiments. Source codes and dataset of this paper will be made publicly available.