Enriching German News Articles with AI-Generated Content

Herold, Nicole; Vogel, Jürgen (14 June 2023). Enriching German News Articles with AI-Generated Content In: SwissText 2023. Neuchâtel, Switzerland. 12 to 14 June 2023.

Text swisstext.pdf Restricted to registered users only Download (311kB) | Request a copy

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.

Item Type:	Conference or Workshop Item (Paper)
Division/Institute:	School of Engineering and Computer Science > Institute for Data Applications and Security (IDAS) > IDAS / Applied Machine Intelligence School of Engineering and Computer Science
Name:	Herold, Nicole and Vogel, Jürgen0009-0006-8150-5888
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Language:	English
Submitter:	Jürgen Vogel
Date Deposited:	18 Dec 2023 13:34
Last Modified:	18 Dec 2023 13:34
ARBOR DOI:	10.24451/arbor.20723
URI:	https://arbor.bfh.ch/id/eprint/20723