Investigating cross-lingual training for offensive language detection
Platforms that feature user-generated content (social media, online forums, newspaper comment sections etc.) have to detect and filter offensive speech within large, fast-changing datasets. While many automatic methods have been proposed and achieve good accuracies, most of these focus on the Englis...
Main Authors: | Andraž Pelicon, Ravi Shekhar, Blaž Škrlj, Matthew Purver, Senja Pollak |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2021-06-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-559.pdf |
Similar Items
-
Zero-Shot Learning for Cross-Lingual News Sentiment Classification
by: Andraž Pelicon, et al.
Published: (2020-08-01) -
Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models
by: Chanhee Lee, et al.
Published: (2021-02-01) -
Cross-Lingual Few-Shot Hate Speech and Offensive Language Detection Using Meta Learning
by: Marzieh Mozafari, et al.
Published: (2022-01-01) -
Cross-Lingual Named Entity Recognition Based on Attention and Adversarial Training
by: Hao Wang, et al.
Published: (2023-02-01) -
Cross-Lingual Passage Re-Ranking With Alignment Augmented Multilingual BERT
by: Dongmei Chen, et al.
Published: (2020-01-01)