Title :
A global optimization framework for meeting summarization
Author :
Gillick, Dan ; Riedhammer, Korbinian ; Favre, Benoit ; Hakkani-Tür, Dilek
Author_Institution :
Comput. Sci. Dept., Univ. of California Berkeley, Berkeley, CA
Abstract :
We introduce a model for extractive meeting summarization based on the hypothesis that utterances convey bits of information, or concepts. Using keyphrases as concepts weighted by frequency, and an integer linear program to determine the best set of utterances, that is, covering as many concepts as possible while satisfying a length constraint, we achieve ROUGE scores at least as good as a ROUGE-based oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.
Keywords :
integer programming; linear programming; text analysis; ROUGE- based oracle; extractive meeting; global optimization framework; human summaries; integer linear program; meeting summarization; Ambient intelligence; Computer science; Data mining; Frequency; Humans; Integer linear programming; integer linear programming; meeting summarization; summarization evaluation;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4960697
