In this paper, we formulate extractive summarization as a risk minimization problem and propose a unified probabilistic framework that naturally combines supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. In addition, the introduction of various loss functions also provides the summarization framework with a flexible but systematic way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. Experiments on speech summarization show that the methods deduced from our framework are very competitive with existing summarization approaches.
|主出版物標題||ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference|
|出版狀態||已發佈 - 2010|
|事件||48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, 瑞典|
持續時間: 2010 七月 11 → 2010 七月 16
|其他||48th Annual Meeting of the Association for Computational Linguistics, ACL 2010|
|期間||2010/07/11 → 2010/07/16|
ASJC Scopus subject areas