论文信息 - A hybrid statistical/linguistic model for generating news story gists

A hybrid statistical/linguistic model for generating news story gists

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.

Eamonn Newman | John Dunnion | Joe Carthy | Nicola Stokes | William P. Doran

[1] John Dunnion,et al. Assessing the Impact of Lexical Chain Scoring Methods and Sentence Extraction Schemes on Summarization , 2004, CICLing.

[2] Nicola Stokes,et al. Applications of Lexical Cohesion Analysis in the Topic Detection and Tracking Domain , 2004 .

[3] Eduard H. Hovy,et al. Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.