@inproceedings{subramanian-etal-2021-team,
    title = "{T}eam{\_}{BUDDI} at {C}om{MA}@{ICON}: Exploring Individual and Joint Modelling Approaches for Detecting Aggression, Communal Bias and Gender Bias",
    author = "Subramanian, Anand  and
      Reghu, Mukesh  and
      Rajkumar, Sriram",
    editor = "Kumar, Ritesh  and
      Singh, Siddharth  and
      Nandi, Enakshi  and
      Ratan, Shyam  and
      Devi, Laishram Niranjana  and
      Lahiri, Bornini  and
      Bansal, Akanksha  and
      Bhagat, Akash  and
      Dawer, Yogesh",
    booktitle = "Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification",
    month = dec,
    year = "2021",
    address = "NIT Silchar",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2021.icon-multigen.2/",
    pages = "13--20",
    abstract = "The ComMA@ICON 2021 Shared Task involved identifying the level of aggression and identifying gender bias and communal bias from texts in various languages from the domain of social media. In this paper, we present the description and analyses of systems we implemented towards these tasks. We built systems utilizing Transformer-based models, experimented by individually and jointly modelling these tasks, and investigated the performance of a feature engineering method in conjunction with a joint modelling approach. We demonstrate that the joint modelling approaches outperform the individual modelling approach in most cases."
}