A risk minimization framework for extractive speech summarization

Shih Hsiang Lin*, Berlin Chen

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

12 引文 斯高帕斯(Scopus)

摘要

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.

原文英語
主出版物標題ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
頁面79-87
頁數9
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 112010 七月 16

其他

其他48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
國家/地區瑞典
城市Uppsala
期間2010/07/112010/07/16

ASJC Scopus subject areas

  • 語言與語言學
  • 語言和語言學

指紋

深入研究「A risk minimization framework for extractive speech summarization」主題。共同形成了獨特的指紋。

引用此