Login
- Autorinnen/Autoren:
- Blanc, Olivier; Pritzkau, Albert; Schade, Ulrich; Geierhos, Michaela
- Dokumenttyp:
- Konferenzbeitrag / Conference Paper
- Titel:
- CODE at CheckThat! 2022: Multi-class fake news detection of news articles with BERT
- Herausgebende Sammelband:
- Faggioli, Guglielmo; Ferro, Nicola; Hanbury, Allan; Potthast, Martin
- Titel Konferenzpublikation:
- Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum
- Untertitel Konferenzpublikation:
- Bologna, Italy, September 5th to 8th, 2022
- Serie/Reihe:
- CEUR Workshop Proceedings
- Band:
- 3180
- Konferenztitel:
- Conference and Labs of the Evaluation Forum (13., 2022, Bologna)
- Tagungsort:
- Bologna, Italy
- Jahr der Konferenz:
- 2022
- Datum Beginn der Konferenz:
- 05.09.2022
- Datum Ende der Konferenz:
- 08.09.2022
- URL zum Konferenzband:
- http://ceur-ws.org/Vol-3180/
- Jahr:
- 2022
- Seitenbereich:
- 444-455
- Sprache:
- Englisch
- Stichwörter:
- Sequence Classification ; Deep Learning ; Transformers ; BERT
- Abstract:
- The following system description presents our approach for detecting fake news in texts. The given task was formulated as a multi-class classification problem. Our approach is based on the combination of two BERT-based classification models: One model determines whether the textual content is relevant to the task; the second model assigns it a truth value. Starting from a pre-trained model for language representation, we fine-tuned these models on the given classification task in supervised tra... »
- ISBN:
- 1613-0073
- URL zum Inhalt:
- http://ceur-ws.org/Vol-3180/paper-34.pdf
- Fakultät:
- Fakultät für Informatik
- Institut:
- INF 7 - Institut für Datensicherheit
- Professorin/Professor:
- Geierhos, Michaela
- Forschungszentrum:
- CODE
- Open Access:
- Ja / Yes
- Open-Access-Lizenz:
- CC BY 4.0
- URL zur Lizenz:
- https://creativecommons.org/licenses/by/4.0/
BibTeX