ES-JUST at SemEval-2021 Task 7: Detecting and Rating Humor and Offensive Text Using Deep Learning

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1102–1107 Bangkok, Thailand (online), August 5–6, 2021. ©2021 Association for Computational Linguistics 1102 ES-JUST at SemEval-2021 Task 7: Detecting and Rating Humor and Offensive Text Using Deep Learning Emran Al Bashabsheh Computer Science Department Jordan University of Science and Technology Irbid, Jordan emranalbashabsheh@gmail.com Sanaa Abu Alasal Computer Science Department Jordan University of Science and Technology Irbid, Jordan sanaasal11@gmail.com Abstract This research presents the work of the team’s ES-JUST at semEval-2021 task 7 for detect- ing and rating humor and offensive text us- ing deep learning. The team evaluates sev- eral approaches (i.e.BERT (Devlin et al., 2018), Roberta (Liu et al., 2019), XLM-Roberta (Con- neau et al., 2019), and BERT embedding + Bi- LSTM) that employ in four sub-tasks. The first sub-task deal with whether the text is humor- ous or not. The second sub-task is the degree of humor in the text if the first sub-task is hu- morous. The third sub-task represents the text is controversial or not if it is humorous. While in the last task is the degree of an offensive in the text. However, Roberta pre-trained model outperforms other approaches and score the highest in all sub-tasks. We rank on the leader board at the evaluation phase are 26, 26, 25, and 9 through 0.9564 F-score, 0.5709 RMSE, 0.4888 F-score, and 0.4467 RMSE results, re- spectively, for each of the first, second, third, and fourth sub-task, respectively. 1 Introduction Dealing with natural languages has long been a challenge and an interesting topic for researchers (Chowdhury, 2003). Understanding and generat- ing languages is part of natural language process- ing (NLP) (Nadkarni et al., 2011). Recently, the language model is able to deal with sequence-to- sequence problems such as question and answer, translation, multiple choice. In addition, it is able to capture complex relationships, semantic meaning, word meaning disambiguation, and word aspect- based (Deng and Liu, 2018). Humorous text is one of the important things we watched every day. It is commonly used to express an opinion on issues (so- cietal, political, sports, and economic), whether in posts on social media platforms, or as advertising for a specific product (Kramer, 2011). In addition, the humor in the text makes the text complex in terms of interpretation and understanding of the text. Because of the manipulation of the meaning of words and the way the text is written to express the sense of humor in the words. On the other hand, understanding the humorous in the text varies ac- cording to the age or gender of the person, or even according to the culture, social status and mentality of the person(Goel and Dolan, 2007). In this task, a dataset was collected in the English language that represents humor and joke in the text and words. We participated in this task to build an approach capable of distinguishing a text that is humorous or not. Here we have explicitly used pre-trained models that deal with the concept of contextual …

Content truncated to 500 words