@inproceedings{GillickRiedhammerFavreetal.2009, author = {Gillick, Dan and Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Global Optimization Framework for Meeting Summarization}, series = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, booktitle = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, pages = {4769 -- 4772}, year = {2009}, 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.}, language = {en} } @inproceedings{RiedhammerGillickFavreetal.2008, author = {Riedhammer, Korbinian and Gillick, Dan and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {Packing the Meeting Summarization Knapsack}, series = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, booktitle = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, pages = {2434 -- 2437}, year = {2008}, abstract = {Despite considerable work in automatic meeting summarization over the last few years, comparing results remains difficult due to varied task conditions and evaluations. To address this issue, we present a method for determining the best possible extractive summary given an evaluation metric like ROUGE. Our oracle system is based on a knapsack-packing framework, and though NP-Hard, can be solved nearly optimally by a genetic algorithm. To frame new research results in a meaningful context, we suggest presenting our oracle results alongside two simple baselines. We show oracle and baseline results for a variety of evaluation scenarios that have recently appeared in this field.}, language = {en} }