Detecting (Un)Important Content for Single-Document News Summarization
This addresses the challenge of creating effective summarizers for news articles where cross-document repetition is absent, benefiting researchers and practitioners in NLP.
The paper tackled the problem of single-document news summarization by developing a method to detect sentence importance, which outperformed a state-of-the-art summarizer and a baseline in evaluations, representing an important advance in this area.
We present a robust approach for detecting 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 document" heuristic, outperforms a state-of-the-art summarizer and the beginning-of-article 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.