LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific\n BERT?

2020/08/03 by Marc Pàmies, Emily Öhman, Pàmies, Marc +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection

paper · pdf · doi:10.48550/arxiv.2008.00805

openalex publication_date 2020/08/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents the different models submitted by the LT@Helsinki team\nfor the SemEval 2020 Shared Task 12. Our team participated in sub-tasks A and\nC; titled offensive language identification and offense target identification,\nrespectively. In both cases we used the so-called Bidirectional Encoder\nRepresentation from Transformer (BERT), a model pre-trained by Google and\nfine-tuned by us on the OLID and SOLID datasets. The results show that\noffensive tweet classification is one of several language-based tasks where\nBERT can achieve state-of-the-art results.\n

Related

• problemConquero at SemEval-2020 Task 12: Transformer and Soft\n label-based approaches
• KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive\n Tweets Using Weighted Ensemble and Fine-Tuned BERT
• UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models
• LIIR at SemEval-2020 Task 12: A Cross-Lingual Augmentation Approach for\n Multilingual Offensive Language Identification
• KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech\n Identification in Social Media