A unified probabilistic generative framework for extractive spoken document summarization

Yi Ting Chen*, Hsuan Sheng Chiu, Hsin Min Wang, 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

1 引文 斯高帕斯(Scopus)

摘要

In this paper, we consider extractive summarization of Chinese broadcast news speech. A unified probabilistic generative framework that combined the sentence generative probability and the sentence prior probability for sentence ranking was proposed. Each sentence of a spoken document to be summarized was treated as a probabilistic generative model for predicting the document. Two different matching strategies, i.e., literal term matching and concept matching, were extensively investigated. We explored the use of the hidden Markov model (HMM) and relevance model (RM) for literal term matching, while the word topical mixture model (WTMM) for concept matching. On the other hand, the confidence scores, structural features, and a set of prosodic features were properly incorporated together using the whole sentence maximum entropy model (WSME) for the estimation of the sentence prior probability. The experiments were performed on the Chinese broadcast news collected in Taiwan. Very promising and encouraging results were initially obtained.

原文英語
主出版物標題International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
頁面2528-2531
頁數4
出版狀態已發佈 - 2007 十二月 1
事件8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, 比利时
持續時間: 2007 八月 272007 八月 31

出版系列

名字International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
4

其他

其他8th Annual Conference of the International Speech Communication Association, Interspeech 2007
國家/地區比利时
城市Antwerp
期間2007/08/272007/08/31

ASJC Scopus subject areas

  • 電腦科學應用
  • 軟體
  • 建模與模擬
  • 語言和語言學
  • 通訊

指紋

深入研究「A unified probabilistic generative framework for extractive spoken document summarization」主題。共同形成了獨特的指紋。

引用此