Detecting Summary-Worthy Sentences: The Effect of Discourse Features

We examine the benefit of a variety of discourse and semantic features for the identification of summary-worthy content in narrative stories. Using logistic regression models, we find that the most informative features are those that relate to the narrative structure of a text. We show that automatic methods for feature extraction perform significantly worse than full manual annotation, but that with optimization, a fully automatic approach can outperform a variety of existing extractive approaches to summarization.

我们研究了多种语篇和语义特征对识别叙事故事中值得总结的内容的益处。通过使用逻辑回归模型，我们发现最具信息量的特征是那些与文本的叙事结构相关的特征。我们表明，自动特征提取方法的性能明显比完全人工标注差，但通过优化，一种全自动方法能够优于多种现有的提取式总结方法。