UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection

Gregor Wiedemann, Seid Muhie Yimam, Chris Biemann


Abstract
Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks. Typically, fine-tuning is performed on task-specific training datasets in a supervised manner. One can also fine-tune in unsupervised manner beforehand by further pre-training the masked language modeling (MLM) task. Hereby, in-domain data for unsupervised MLM resembling the actual classification target dataset allows for domain adaptation of the model. In this paper, we compare current pre-trained transformer networks with and without MLM fine-tuning on their performance for offensive language detection. Our MLM fine-tuned RoBERTa-based classifier officially ranks 1st in the SemEval 2020 Shared Task 12 for the English language. Further experiments with the ALBERT model even surpass this result.
Anthology ID:
2020.semeval-1.213
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Venues:
COLING | SemEval
SIGs:
SIGSEM | SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
1638–1644
Language:
URL:
https://aclanthology.org/2020.semeval-1.213
DOI:
10.18653/v1/2020.semeval-1.213
Bibkey:
Cite (ACL):
Gregor Wiedemann, Seid Muhie Yimam, and Chris Biemann. 2020. UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1638–1644, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection (Wiedemann et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.213.pdf
Data
OLID