IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1221–1225 Bangkok, Thailand (online), August 5–6, 2021. ©2021 Association for Computational Linguistics 1221 IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining Tathagata Raha, Ishan Sanjeev Upadhyay, Radhika Mamidi, Vasudeva Varma IIIT Hyderabad, India, {tathagata.raha, ishan.sanjeev}@research.iiit.ac.in {radhika.mamidi, vv}@iiit.ac.in Abstract This paper describes our approach (IIITH) for SemEval-2021 Task 5: HaHackathon: Detect- ing and Rating Humor and Offense. Our re- sults focus on two major objectives: (i) Ef- fect of task adaptive pretraining on the perfor- mance of transformer based models (ii) How does lexical and hurtlex features help in quan- tifying humour and offense. In this paper, we provide a detailed description of our approach along with comparisions mentioned above. 1 Introduction Humour is an important part of human conversa- tion. It has a social function as well and can play an important role in group cohesiveness(Ziv, 2010). Hence humorous content is also found on various social media websites. While there has always been a fine line between funny and offensive humour, the anonymity, distance and isolation provided by being online can increase instances of offensive or controversial humour being posted online. (Weitz, 2017) In this task, we have presented a transformer based approach combined with lexical and hurtlex feature sets to quantify humour and offense of a piece of text. We achieved an F1 score of 0.959 in the humor classification task and 0.592 in the humor contro- versy task. For the regression tasks, we achieved a RMSE score of 0.541 and 0.488 in the humor regression and offense regression task respectively. 2 Related work There have been many attempts made at compu- tational humour detection. In this section, we briefly describe other work in this area. In this approach(Blinov et al., 2019), the authors have used universal language model fine-tuning method for humour recognition. Convolutional neural net- works (CNN) have also been used for this task by (Chen and Soo, 2018) whereas (Weller and Seppi, 2019) used transformers to classify humour. There has also been a lot of shared tasks and workshops related to computational humour. One of them is SemEval-2020 Task 7: Assessing Humor in Edited News Headlines(Hossain et al., 2020) where Zhang(Zhang et al., 2020) used bidirectional neural networks with an attention mechanism and incorporated lexical features to assess humour in edited news headlines. There has been a lot of work done on hate speech and offensive speech detection as well. CNN’s and gated recurrent units (GRU) have been used for this task (Zhang and Luo, 2018). Recurrent neural networks combined with user-related information have also been used for hate speech detection in Twitter Data (Pitsilis et al., 2018) whereas multilin- gual transformer architectures were leveraged by (Ghosh Roy et al., 2021) to detect hostile content in English, Hindi and German. 3 Task and dataset overview The task(Meaney et al., 2021) is divided into 4 sub-tasks. 1. Humour detection: This is a …

Content truncated to 500 words