A multi-task Arabic offensive speech detector with entropy-based active learning and weighted emoji tokens reports 85.42% macro F1 on OSACT2022 using roughly 3,300 training samples.
A survey on automatic detection of hate speech in text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-task Learning with Active Learning for Arabic Offensive Speech Detection
A multi-task Arabic offensive speech detector with entropy-based active learning and weighted emoji tokens reports 85.42% macro F1 on OSACT2022 using roughly 3,300 training samples.