|
|
|
                                          
|
Return to Posters
In this paper, we describe a News Story Gisting system that generates a 10-word short summary of a news story. This system uses a machine learning technique to combine linguistic, statistical and positional information in order to generate an appropriate summary. We also present the results of an automatic evaluation of this system with respect to the performance of other baseline summarisers using the new ROUGE evaluation metric.
@inproceedings{1009072, author = {William P. Doran and Nicola Stokes and Eamonn Newman and John Dunnion and Joe Carthy}, title = {A hybrid statistical/linguistic model for generating news story gists}, booktitle = {SIGIR '04: Proceedings of the 27th annual international conference on Research and development in information retrieval}, year = {2004}, isbn = {1-58113-881-4}, pages = {464--465}, location = {Sheffield, United Kingdom}, doi = {http://doi.acm.org/10.1145/1008992.1009072}, publisher = {ACM Press}, }  ©2005 Association for Computing Machinery |
