problemConquero at SemEval-2020 Task 12: Transformer and Soft Label-based Approaches

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 2123–2132 Barcelona, Spain (Online), December 12, 2020. 2123 problemConquero at SemEval-2020 Task 12: Transformer and Soft label-based approaches Karishma Laud∗ Jagriti Singh∗ Randeep Kumar Sahu Ashutosh Modi Indian Institute of Technology Kanpur (IITK) {kslaud,jagriti,randeeps}@iitk.ac.in ashutoshm@cse.iitk.ac.in Abstract In this paper, we present various systems submitted by our team problemConquero for SemEval-2020 Shared Task 12 “Multilingual Offensive Language Identification in Social Media”. We participated in all the three sub-tasks of OffensEval-2020, and our final submissions during the evaluation phase included transformer-based approaches and a soft label-based approach. BERT based fine-tuned models were submitted for each language of sub-task A (offensive tweet identification). RoBERTa based fine-tuned model for sub-task B (automatic categorization of offense types) was submitted. We submitted two models for sub-task C (offense target identification), one using soft labels and the other using BERT based fine-tuned model. Our ranks for sub-task A were Greek-19 out of 37, Turkish-22 out of 46, Danish-26 out of 39, Arabic-39 out of 53, and English-20 out of 85. We achieved a rank of 28 out of 43 for sub-task B. Our best rank for sub-task C was 20 out of 39 using BERT based fine-tuned model. 1 Introduction There has been a rise in the use of offensive language on social media platforms. This discourages effective communication, which comes as a drawback against the goal of social media platforms. Hence a need to address the problem of offensive language identification arises. There has been an increasing awareness in communities to filter and moderate tweets. As huge number of users are online, it is difficult to manually moderate each and every content; hence the need for automation arises. As people from different regions, ethnicity interact with each other on online platforms, the detection of multilingual offensive language has become increasingly important. During the training phase of the competition, we started with various machine learning models and proceeded with the model in the evaluation phase, which gave us the highest macro F1 score on the development set. In this paper, we first describe the existing work that has been done for offensive language detection, our proposed approaches, and the results that we obtained. The implementation for our system is made available via Github1. 2 Problem Defintion OffensEval-2020 (Zampieri et al., 2020) consisted of 3 sub-tasks. 1. Sub-task A was to classify a tweet as offensive (OFF) or not offensive (NOT). Sub-task A was carried out in five languages: English, Danish, Greek, Turkish, and Arabic. 2. Sub-task B was a classification problem that categorized offensive labeled tweet as targeted (insult or threat) or non-targeted (swear words). 3. Sub-task C was a multi-classification problem that classified the targeted offensive tweet as individual (IND), group (GRP) or others (OTH). ∗ Authors equally contributed to this work. This work is licensed under a Creative Commons Attribution 4.0 International License. License details: http:// creativecommons.org/licenses/by/4.0/. 1https://github.com/karishmaslaud/OffensEval 2124 3 Related Work Offensive language detection has been studied at various levels of granularity in the …

Content truncated to 500 words