Repository logo
  • English
  • Deutsch
  • Français
Log In
New user? Click here to register.Have you forgotten your password?
  1. Home
  2. CRIS
  3. Publication
  4. Enriching German News Articles with AI-Generated Content
 

Enriching German News Articles with AI-Generated Content

URI
https://arbor.bfh.ch/handle/arbor/35931
Version
Published
Date Issued
2023-06-14
Author(s)
Herold, Nicole
Vogel, Jürgen  
Type
Conference Paper
Language
English
Abstract
Newspapers or magazines currently often publish articles in print or online in almost identical versions, maybe just adding links to related content or a user forum online. For further enriching the original article, we investigated methods to create different types of content automatically with state-of-the-art generative language models: (1) Keynotes, (2) a summary, and (3) a content-related quiz (i.e., a question with answers). Our study is based on 2.5k German articles from the Swiss daily newspaper ”Tages-Anzeiger”. Our evaluation with a professional editor showed that content generated by ChatGPT from OpenAI outperformed traditional NLP methods as well as human-generated content.
Subjects
QA75 Electronic computers. Computer science
DOI
10.24451/arbor.20723
https://doi.org/10.24451/arbor.20723
Publisher URL
https://www.swisstext.org/swisstext.org/2023/
Organization
IDAS / Applied Machine Intelligence  
Technik und Informatik  
Conference
SwissText 2023
Submitter
VogelJ
Citation apa
Herold, N., & Vogel, J. (2023). Enriching German News Articles with AI-Generated Content. SwissText 2023. https://doi.org/10.24451/arbor.20723
File(s)
Loading...
Thumbnail Image

restricted

Name

swisstext.pdf

Size

304.09 KB

Format

Adobe PDF

Checksum (MD5)

0c1bb0753ec209ad836deee9db0a647f

About ARBOR

Built with DSpace-CRIS software - System hosted and mantained by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement
  • Send Feedback
  • Our institution