UJNLP at SemEval-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 2203–2208 Barcelona, Spain (Online), December 12, 2020. 2203 UJNLP at SemEval-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers Yinnan Yao School of Information Science and Engineering University of Jinan yaoyinnan@foxmail.com Nan Su School of Information Science and Engineering University of Jinan me@sunan.me Kun Ma∗ Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan ise mak@ujn.edu.cn Abstract In this paper, we built several pre-trained models to participate SemEval-2020 Task 12: Multi- lingual Offensive Language Identification in Social Media. In the common task of Offensive Language Identification in Social Media, pre-trained models such as Bidirectional Encoder Repre- sentation from Transformer (BERT) have achieved good results. We preprocess the dataset by the language habits of users in social network. Considering the data imbalance in OffensEval, we screened the newly provided machine annotation samples to construct a new dataset. We use the dataset to fine-tune the Robustly Optimized BERT Pretraining Approach (RoBERTa). For the English subtask B, we adopted the method of adding Auxiliary Sentences (AS) to transform the single-sentence classification task into a relationship recognition task between sentences. Our team UJNLP wins the ranking 16th of 85 in English subtask A (Offensive language identification) . 1 Introduction With the explosive growth of data generated by online social network users, the malicious content mixed in the information published by users has brought great challenges to the detection of hate speech and offensive language. Due to the difference between social media and traditional media, users are allowed to post information at will. The emergence of large amounts of data invalidates manual review, resulting in a large number of methods that use machine learning for automatic classification. Therefore, SemEval 2020 released OffensEval2 (Zampieri et al., 2020), which compared to OffensEval (Zampieri et al., 2019b) increased the size of the dataset and added multilingual. Multilingual data sets have been added in OffensEval2, includes Arabic (Mubarak et al., 2020), Danish (Sigurbergsson and Derczynski, 2020), English (Rosenthal et al., 2020), Greek (Pitenis et al., 2020), and Turkish (C¸ ¨oltekin, 2020). This task of English is divided into three subtasks: offensive language recognition, automatic classification of attack types, and attack target recognition. Our method for this task of English is based on BERT and RoBERTa. The organizer provided a large number of samples marked by the machine and included the confidence of each sample. Because deep neural networks rely on large-scale datasets, the results obtained when using only the OLID dataset are not ideal. Due to equipment limitations and considering the error of machine labeling samples, we did not use all data for training. Based on the OLID dataset (Zampieri et al., 2019a), we use the data with a confidence higher than threshold to expand the dataset to make the number of positive and negative samples equal to avoid the problems caused by the balance of dataset. For subtask B, we add Auxiliary Sentences(AS) to transform the single-sentence classification task into a problem of relationship recognition …

Content truncated to 500 words