Headline Generation for Written and Broadcast News
| Title | Headline Generation for Written and Broadcast News |
| Publication Type | Reports |
| Year of Publication | 2005 |
| Authors | Zajic D, Dorr BJ, Schwartz R |
| Date Published | 2005/03// |
| Institution | Instititue for Advanced Computer Studies, Univ of Maryland, College Park |
| Keywords | *INFORMATION RETRIEVAL, *RADIO BROADCASTING, AUTOMATIC, AUTOMATIC SUMMARIZATION, HEDGE TRIMMER, INFORMATION SCIENCE, RADIO COMMUNICATIONS, STATISTICAL PROCESSES, TEST AND EVALUATION, WORDS(LANGUAGE) |
| Abstract | This technical report is an overview of work done on Headline Generation for written and broadcast news. The report covers HMM Hedge, a statistical approach based on the noisy channel model, Hedge Trimmer, a parse-and-trim approach using linguistically motivated trimming rules, and Topiary, a combination of Trimmer and Unsupervised Topic Discovery. Automatic evaluation of summaries using ROUGE and BLEU is described and used to evaluate the Headline Generation systems. |
| URL | http://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA454198 |