Name
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. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICASSP.2009.4960697 | ICASSP |
Keywords | Field | DocType |
length constraint,integer linear program,critical discussion,best set,summarization evaluation,extractive meeting summarization,index terms— meeting summarization,rouge score,integer linear program- ming,human summary,rouge-based oracle,global optimization framework,artificial neural networks,redundancy,ambient intelligence,integer linear programming,text analysis,frequency,indexing terms,satisfiability,speech,global optimization,integer programming,linear programming,data mining,computer science | Computer science,Oracle,Integer programming,Redundancy (engineering),Artificial intelligence,Linear programming,Natural language processing,Artificial neural network,Automatic summarization,Mathematical optimization,Global optimization,Ambient intelligence,Machine learning | Conference |
ISSN | Citations | PageRank |
1520-6149 | 38 | 1.21 |
References | Authors | |
11 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dan Gillick | 1 | 257 | 11.96 |
| Korbinian Riedhammer | 2 | 244 | 15.53 |
| Benoit Favre | 3 | 133 | 8.58 |
| Dilek Hakkani-Tür | 4 | 282 | 17.30 |