We present a robust approach for detect ing intrinsic sentence importance in news, by training on two corpora of document-summary pairs. When used for single-document summarization, our approach, combined with the "beginning of docu ment" heuristic, outperforms a state-of-the-art summarizer and the beginning-of-article baseline in both automatic and manual evaluations. These results repre sent an important advance because in the absence of cross-document repetition, sin gle document summarizers for news have not been able to consistently outperform the strong beginning-of-article baseline.
展开▼
