Amsqr at SemEval-2020 Task 12: Offensive Language Detection Using Neural Networks and Anti-adversarial Features

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 1898–1905 Barcelona, Spain (Online), December 12, 2020. 1898 amsqr at SemEval-2020 Task 12: Offensive language detection using neural networks and anti-adversarial features Alejandro Mosquera Symantec Enterprise Division Broadcom Corporation alejandro.mosquera@broadcom.com Abstract This paper describes a method and system to solve the problem of detecting offensive language in social media using anti-adversarial features. Our submission to the SemEval-2020 task 12 challenge was generated by an stacked ensemble of neural networks fine-tuned on the OLID dataset and additional external sources. For Task-A (English), text normalisation filters were applied at both graphical and lexical level. The normalisation step effectively mitigates not only the natural presence of lexical variants but also intentional attempts to bypass moderation by introducing out of vocabulary words. Our approach provides strong F1 scores for both 2020 (0.9134) and 2019 (0.8258) challenges. 1 Introduction Keeping social media platforms free from unwanted publications such as spam, scam, phishing, hate speech, targeted attacks and fake news is still an active research topic nowadays. This is due not only to the relative low cost of creating fake accounts, bots (Albadi et al., 2019) and forging online identi- ties but also to the large amount of personal information made available on the Internet which makes targeting certain groups and individuals easier than ever. While some of these threats were seen before affecting traditional messaging platforms such as email and SMS, the reach and adoption of social media applications have amplified their impact, requiring additional cost and effort to mitigate. The use of offensive language as a vehicle to attack individuals and communities poses challenges not only for humans, which are prone to subjective and biased judgement (Sap et al., 2019) but also for automatic moderation systems. The inherent ambiguity when dealing with messages which are often short, can be written in mixed languages, contain informal words and are usually subject to adversarial modifications render na¨ıve filtering approaches such as word lists or re-purposed spam detection models ineffective. For this reason, in order to solve this problem more sophisticated approaches such as state of the art natural language processing (NLP) is needed. In order to keep track and measure the progress in the area on offensive language detection several English datasets with annotations for hate (Davidson et al., 2017), (Waseem and Hovy, 2016), targeted (Zampieri et al., 2019a) and personal attacks (Wulczyn et al., 2016) were released over the last years. Likewise, public evaluations such as HatEval (Basile et al., 2019) and OffenseEval (Zampieri et al., 2019b) were recently introduced highlighting the need for stronger baselines to assess the performance of more complex systems. This paper evaluates the method and system submitted to the shared task 12 of SemEval-2020: Mul- tilingual Offensive Language Identification in Social Media (Zampieri et al., 2020) for the subtask A (English) based on an stacked ensemble of neural networks. The rest of the document is organised as follows: In section 2, we review related work relevant for detecting abusive language. …

Content truncated to 500 words