A global optimization framework for meeting summarization

14 years 5 months ago

Download www.icsi.berkeley.edu

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 ROUGEbased oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.

Daniel Gillick, Korbinian Riedhammer, Benoît

Real-time Traffic

Convey Bits | Extractive Meeting Summarization | ICASSP 2009 | Integer Linear Program | Signal Processing |

claim paper

» A Study of Global Inference Algorithms in Multidocument Summarization

» Inter and Intramodal Deformable Registration Continuous Deformations Meet Efficient Optima...

» FedX A Federation Layer for Distributed Query Processing on Linked Open Data

» Global Critical Path A Tool for SystemLevel Timing Analysis

» CrossLayer Optimization for Video Summary Transmission over Wireless Networks

» A Framework for Compiler Driven Design Space Exploration for Embedded System Customization

» A heuristicbased framework to solve a complex aircraft sizing problem

» A CrossLayer Approach for PowerPerformance Optimization in Distributed Mobile Systems

Post Info
More Details (n/a)

Added	21 May 2010
Updated	21 May 2010
Type	Conference
Year	2009
Where	ICASSP
Authors	Daniel Gillick, Korbinian Riedhammer, Benoît Favre, Dilek Z. Hakkani-Tür

Comments (0)

Sciweavers

A global optimization framework for meeting summarization

Convey Bits | Extractive Meeting Summarization | ICASSP 2009 | Integer Linear Program | Signal Processing |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers