Sciweavers

Share
ICASSP
2010
IEEE

Leveraging evaluation metric-related training criteria for speech summarization

11 years 6 months ago
Leveraging evaluation metric-related training criteria for speech summarization
Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem and have shown empirical success for a wide variety of summarization tasks. However, the imbalanceddata problem sometimes results in a trained speech summarizer with unsatisfactory performance. On the other hand, training the summarizer by improving the associated classification accuracy does not always lead to better summarization evaluation performance. In view of such phenomena, we hence investigate two different training criteria to alleviate the negative effects caused by them, as well as to boost the summarizer’s performance. One is to learn the classification capability of a summarizer on the basis of the pair-wise ordering information of sentences in a training document according to a degree of importance. The other is to train the summarizer by directly maximizing the associated evaluation score. Experimental results on the broadca...
Shih-Hsiang Lin, Yu-Mei Chang, Jia-Wen Liu, Berlin
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Shih-Hsiang Lin, Yu-Mei Chang, Jia-Wen Liu, Berlin Chen
Comments (0)
books