Headline Generation for Written and Broadcast News

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2005
Accession Number
ADA454198

Entities

People

  • Bonnie J. Dorr
  • David Zajic
  • Richard Schwartz

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Biomedical
  • Weapons Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Automated Text Summarization
  • Birds
  • Computational Linguistics
  • Computational Science
  • Decoding
  • Demographic Cohorts
  • Governments
  • Hidden Markov Models
  • Hong Kong
  • Language
  • Machine Learning
  • Machine Translation
  • Markov Models
  • Materials
  • Motor Skills
  • Probability

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • International Journalism and Media Studies.
  • Software Engineering