UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction
In: 2021.semeval-1.28 (2021) 243-248; (2021)
Online
report
Zugriff:
Toxicity is pervasive in social media and poses a major threat to the health of online communities. The recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the way in which we approach natural language processing. However, the inherent nature of pre-training means that they are unlikely to capture task-specific statistical information or learn domain-specific knowledge. Additionally, most implementations of these models typically do not employ conditional random fields, a method for simultaneous token classification. We show that these modifications can improve model performance on the Toxic Spans Detection task at SemEval-2021 to achieve a score within 4 percentage points of the top performing team.
Comment: Published in Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021); Code available at: https://github.com/erikdyan/toxic_span_detection
Titel: |
UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction
|
---|---|
Autor/in / Beteiligte Person: | Yan, Erik ; Madabushi, Harish Tayyar |
Link: | |
Quelle: | 2021.semeval-1.28 (2021) 243-248; (2021) |
Veröffentlichung: | 2021 |
Medientyp: | report |
DOI: | 10.18653/v1/2021.semeval-1.28 |
Schlagwort: |
|
Sonstiges: |
|