iCompass at SemEval-2020 Task 12: From a Syntax-ignorant N-gram Embeddings Model to a Deep Bidirectional Language Model

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 1978–1982 Barcelona, Spain (Online), December 12, 2020. 1978 iCompass at SemEval-2020 Task 12: From a Syntax-ignorant N-gram Embeddings Model to a Deep Bidirectional Language Model Abir Messaoudi iCompass / Tunisia abir@icompass.com Hatem Haddad iCompass / Tunisia hatem@icompass.tn Moez Ben Hajhmida iCompass / Tunisia moez@icompass.tn Abstract We describe our submitted system to the SemEval 2020. We tackled Task 12 entitled “Multilingual Offensive Language Identification in Social Media”, specifically subtask 4A-Arabic. We propose three Arabic offensive language identification models: Tw-StAR, BERT and BERT+BiLSTM. Two Arabic abusive/hate datasets were added to the training dataset: L-HSAB and T-HSAB. The final submission was chosen based on the best performances which was achieved by the BERT+BiLSTM model. 1 Introduction With the freedom of expression privilege granted after the Arab countries revolution, sensitive topics such as religion and politics have become popular and widely discussed across social media platforms. However, on the down side, offensive language spreads easily. Indeed, recent events; like Persian’s gulf crisis, the parliamentary-presidential elections held in Tunisia or a football game between two Arabic clubs; caused intensive debates, most of them took place on social media networks leading to a high emergence of offensive speech. This evokes the need for tools to identify such online offensive language content. Analyzing Arabic offensive language is significantly challenging due to the complex nature and morphology of the Arabic language. Furthermore, Arabic language in Social Media is mostly informal and written in Arabic dialects. We describe our participation in SemEval 2020 Task 12 entitled “Multilingual Offensive Language Identification in Social Media” Zampieri et al. (2020), specifically Task 12 4A-Arabic: ”Arabic Offensive Language Identification in Social Media” Mubarak et al. (2020) under the team name “iCompass”. The task requires to distinguish between offensive (containing any form of non-acceptable language (profanity)) and non-offensive posts. The remainder of the paper is organized as follows: in Section 2, we introduce L-HSAB and T-HSAB datasets. In Section 3, we describe the preprocessing step. Section 4 introduces the learning strategies and datasets used in the presented models. Results are reviewed and discussed in Section 5 while Section 6 concludes the study. 2 Arabic offensive language datasets The proposed dataset for the SemEval task 12 subtask A-Arabic is composed mainly by Egyptian dialect comments and few other dialects like Libyan, Sudanese, Syrian, etc. Some comments, after the preprocessing phase, in different dialects are given in Table 11. Consequently, in addition to the dataset proposed by SemEval Task 12 4A-Arabic, we used two other Arabic offensive language datasets : L-HSAB and T-HSAB. L-HSAB (a Twitter dataset about abusive speech (AS) and hate speech (HS)) is introduced in Mulki et al. (2019a) as a benchmark dataset for automatic detection of online Levantine offensive language. The This work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http:// creativecommons.org/licenses/by/4.0/. 1Comments numbers 700, 1088, 5 and 2439 of the training set. 1979 Dialect Comment English translation Egyptian .��� ��� �� ��� �� ��� �� ��� …

Content truncated to 500 words