1 code implementation • Findings (EMNLP) 2021 • Timo Spinde, Manuel Plank, Jan-David Krieger, Terry Ruas, Bela Gipp, Akiko Aizawa
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
1 code implementation • 29 Sep 2022 • Timo Spinde, Manuel Plank, Jan-David Krieger, Terry Ruas, Bela Gipp, Akiko Aizawa
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
no code implementations • 14 Dec 2021 • Timo Spinde, David Krieger, Manuel Plank, Bela Gipp
Our results demonstrate the existing crowdsourcing approaches' lack of data quality, underlining the need for a trained expert framework to gather a more reliable dataset.