The Research group of Dr. Jasbanta Patro, Department of Data Science and Engineering developed Hate detection has long been a challenging task for the NLP community. The task becomes complex in a code-mixed environment because the models must understand the context and the hate expressed through language alteration. Compared to the single language setup, we see much less work on code-mixed hate as large-scale annotated hate corpora are unavailable for the study. To overcome this bottleneck, Dr Jasabanta Patro’s lab in DSE proposed a unique strategy where they relied on native language hate samples to improve code-mixed hate performance. They hypothesised that in the era of multilingual language models (MLMs), hate in code-mixed settings can be detected by majorly relying on native language samples. This work has been recently published in ACM TALLIP. More details at https://dl.acm.org/doi/pdf/10.1145/3726866
