TY - GEN
T1 - Learning deep rhetorical structure for extractive speech summarization
AU - Zhang, Justin Jian
AU - Fung, Pascale
PY - 2010
Y1 - 2010
N2 - Extractive summarization of conference and lecture speech is useful for online learning and references. We show for the first time that deep(er) rhetorical parsing of conference speech is possible and helpful to extractive summarization task. This type of rhetorical structures is evident in the corresponding presentation slide structures. We propose using Hidden Markov SVM (HMSVM) to iteratively learn the rhetorical structure of the speeches and summarize them. We show that system based on HMSVM gives a 64.3% ROUGE-L F-measure, a 10.1% absolute increase in lecture speech summarization performance compared with the baseline system without rhetorical information. Our method equally outperforms the baseline with a conventional discourse feature. Our proposed approach is more efficient than and also improves upon a previous method of using shallow rhetorical structure parsing [1].
AB - Extractive summarization of conference and lecture speech is useful for online learning and references. We show for the first time that deep(er) rhetorical parsing of conference speech is possible and helpful to extractive summarization task. This type of rhetorical structures is evident in the corresponding presentation slide structures. We propose using Hidden Markov SVM (HMSVM) to iteratively learn the rhetorical structure of the speeches and summarize them. We show that system based on HMSVM gives a 64.3% ROUGE-L F-measure, a 10.1% absolute increase in lecture speech summarization performance compared with the baseline system without rhetorical information. Our method equally outperforms the baseline with a conventional discourse feature. Our proposed approach is more efficient than and also improves upon a previous method of using shallow rhetorical structure parsing [1].
KW - Lecture speech summarization
KW - Rhetorical structure
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000287096005054
UR - https://openalex.org/W2070950933
UR - https://www.scopus.com/pages/publications/78049390752
U2 - 10.1109/ICASSP.2010.5494970
DO - 10.1109/ICASSP.2010.5494970
M3 - Conference Paper published in a book
SN - 9781424442966
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5302
EP - 5305
BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Y2 - 14 March 2010 through 19 March 2010
ER -