@inproceedings{garain-etal-2021-junlp,
    title = "{JUNLP}@{D}ravidian{L}ang{T}ech-{EACL}2021: Offensive Language Identification in {D}ravidian Langauges",
    author = "Garain, Avishek  and
      Mandal, Atanu  and
      Naskar, Sudip Kumar",
    editor = "Chakravarthi, Bharathi Raja  and
      Priyadharshini, Ruba  and
      Kumar M, Anand  and
      Krishnamurthy, Parameswari  and
      Sherly, Elizabeth",
    booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
    month = apr,
    year = "2021",
    address = "Kyiv",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.dravidianlangtech-1.46/",
    pages = "319--322",
    abstract = "Offensive language identification has been an active area of research in natural language processing. With the emergence of multiple social media platforms offensive language identification has emerged as a need of the hour. Traditional offensive language identification models fail to deliver acceptable results as social media contents are largely in multilingual and are code-mixed in nature. This paper tries to resolve this problem by using IndicBERT and BERT architectures, to facilitate identification of offensive languages for Kannada-English, Malayalam-English, and Tamil-English code-mixed language pairs extracted from social media. The presented approach when evaluated on the test corpus provided precision, recall, and F1 score for language pair Kannada-English as 0.62, 0.71, and 0.66, respectively, for language pair Malayalam-English as 0.77, 0.43, and 0.53, respectively, and for Tamil-English as 0.71, 0.74, and 0.72, respectively."
}