Contributions to Proceedings:
K. A. Gemes, G. Recski:
"TUW-Inf at GermEval2021: Rule-based and Hybrid Methods for Detecting Toxic, Engaging, and Fact-Claiming Comments";
in: "Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021",
netlibrary,
2021,
69
- 75.
English abstract:
This paper describes our methods submitted for the GermEval 2021 shared task on identifying toxic, engaging and fact-claiming comments in social media texts. We explore simple strategies for semi-automatic generation of rule-based systems with high precision and low recall, and use them to achieve slight overall improvements over a standard BERT-based classifier.
Keywords:
toxic language detection, social media data, rule-based system, deep learning system
"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)
http://dx.doi.org/10.48415/2021/fhw5-x128
Electronic version of the publication:
https://netlibrary.aau.at/obvukloa/content/pageview/6435282
Created from the Publication Database of the Vienna University of Technology.