YNU-HPCC at SemEval-2019 Task 6: Identifying and Categorising Offensive Language on Twitter

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 812–817 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 812 YNU-HPCC at SemEval-2019 Task 6: Identifying and Categorising Offensive Language on Twitter Chengjin Zhou, Jin Wang and Xuejie Zhang School of Information Science and Engineering Yunnan University Contact:Kunming, P.R. China xjzhang@ynu.edu.cn Abstract This document describes the submission of team YNU-HPCC to SemEval-2019 for three Sub-tasks of Task 6: Sub-task A, Sub-task B, and Sub-task C. We have submitted four sys- tems to identify and categorise offensive lan- guage. The first subsystem is an attention- based 2-layer bidirectional long short-term memory (BiLSTM). The second subsystem is a voting ensemble of four different deep learn- ing architectures. The third subsystem is a s- tacking ensemble of four different deep learn- ing architectures. Finally, the fourth subsys- tem is a bidirectional encoder representation- s from transformers (BERT) model. Among our models, in Sub-task A, our first subsys- tem performed the best, ranking 16th among 103 teams; in Sub-task B, the second subsys- tem performed the best, ranking 12th among 75 teams; in Sub-task C, the fourth subsystem performed best, ranking 4th among 65 teams. 1 Introduction Identifying offensive language (Zampieri et al., 2019b) on Twitter is a particularly challenging task because of the informal and creative writing style, with the improper use of grammar, figu- rative language, misspellings and slang, etc. In previous attempts of the task, OffensEval was generally tackled using hand-crafted features and/or sentiment lexicons by feeding them to classifiers such as Support Vector Machines (SVM). These approaches require a laborious feature-engineering process, which may also need domain-specific knowledge, usually resulting in both redundant and missing features. However, in recent years, artificial neural networks for feature learning have achieved good results in this field (Christos Baziotis, 2017). SemEval-2019 Task 6 consists of three Sub- tasks (Symeon Symeonidis, 2017): • Sub-task A: Offensive language identifica- tion; • Sub-task B: Automatic categorisation of of- fense types; • Sub-task C: Offense target identification. In this document, we present four systems that competed at SemEval-2019 Task 6 (Zampieri et al., 2019b). The first model is a 2-layer BiLSTM, equipped with an attention mechanism. The second is voting scheme that combines a 2-layer BiLSTM, Capsule Network, 2-layer bidirectional gated recurrent unit (BiGRU), and the first model. The third model is a stacking scheme that combines a 2-layer BiLSTM, Capsule Network, 2-layer bidirectional gated recurrent unit (BiGRU), and the first model. In addition, the above three models, for the word representation, we have used the glove vector. The fourth model is BERT-BASE (Jacob Devlin, 2018), which was released last year by Google AI Language. The remainder of this document is organised as follows. The related work is described in Section 2. Section 3 reports our methodology and data. Section 4 reports our result. The conclusions are summarised in Section 5. 2 Related Work In recent years, with the rapid development of social media, the use of aggressive and offensive language as well as …

Content truncated to 500 words