A Question of Style: A Dataset for Analyzing Formality on Different Levels

Elisabeth Eder, Ulrike Krieg-Holz, Michael Wiegand


Abstract
Accounting for different degrees of formality is crucial for producing contextually appropriate language. To assist NLP applications concerned with this problem and formality analysis in general, we present the first dataset of sentences from a wide range of genres assessed on a continuous informal-formal scale via comparative judgments. It is the first corpus with a comprehensive perspective on German sentence-level formality overall. We compare machine learning models for formality scoring, a task we treat as a regression problem, on our dataset. Finally, we investigate the relation between sentence- and document-level formality and evaluate leveraging sentence-based annotations for assessing formality on documents.
Anthology ID:
2023.findings-eacl.42
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
580–593
Language:
URL:
https://aclanthology.org/2023.findings-eacl.42
DOI:
10.18653/v1/2023.findings-eacl.42
Bibkey:
Cite (ACL):
Elisabeth Eder, Ulrike Krieg-Holz, and Michael Wiegand. 2023. A Question of Style: A Dataset for Analyzing Formality on Different Levels. In Findings of the Association for Computational Linguistics: EACL 2023, pages 580–593, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
A Question of Style: A Dataset for Analyzing Formality on Different Levels (Eder et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.42.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.42.mp4