Acoustics, Speech, and Signal Processing, IEEE International Conference on (2009)
Apr. 19, 2009 to Apr. 24, 2009
Dan Gillick , Computer Science Dept., University of California Berkeley, USA
Korbinian Riedhammer , Computer Science Dept. 5, University of Erlangen-Nuremberg, GERMANY
Benoit Favre , International Computer Science Institute, Berkeley, USA
Dilek Hakkani-Tur , International Computer Science Institute, Berkeley, USA
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.
K. Riedhammer, D. Gillick, D. Hakkani-Tur and B. Favre, "A global optimization framework for meeting summarization," Acoustics, Speech, and Signal Processing, IEEE International Conference on(ICASSP), Taipei, Taiwan, 2009, pp. 4769-4772.