Detecting (Un)Important content for single-document news summarization

Abstract

We present a robust approach for detecting intrinsic sentence importance in news, by training on two corpora of documentsummary pairs. When used for singledocument summarization, our approach, combined with the "beginning of document" heuristic, outperforms a state-ofthe- art summarizer and the beginning-ofarticle baseline in both automatic and manual evaluations. These results represent an important advance because in the absence of cross-document repetition, single document summarizers for news have not been able to consistently outperform the strong beginning-of-article baseline.