TY - GEN
T1 - Leveraging evaluation metric-related training criteria for speech summarization
AU - Lin, Shih Hsiang
AU - Chang, Yu Mei
AU - Liu, Jia Wen
AU - Chen, Berlin
PY - 2010
Y1 - 2010
N2 - 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 imbalanced-data 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 broadcast news summarization task show that these two training criteria can give substantial improvements over the baseline SVM summarization system.
AB - 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 imbalanced-data 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 broadcast news summarization task show that these two training criteria can give substantial improvements over the baseline SVM summarization system.
KW - Evaluation metric
KW - Imbalanced-data
KW - Ranking capability
KW - Sentence-classification
KW - Speech summarization
UR - http://www.scopus.com/inward/record.url?scp=78049393720&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78049393720&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2010.5494956
DO - 10.1109/ICASSP.2010.5494956
M3 - Conference contribution
AN - SCOPUS:78049393720
SN - 9781424442966
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5314
EP - 5317
BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Y2 - 14 March 2010 through 19 March 2010
ER -