A team of 8 students – Aditya Kadam (UG3, Anmol Goel (RA), Jivitesh Jain (UG4), Mallika Subramanian (UG4), Manvith Reddy (UG4), Prashant Kodali (Ph.D), Arjun T H (UG3), Jushaan Singh Kalra (UG4, Delhi Technological University) and faculty members Prof. Ponnurangam Kumaraguru and Prof. Manish Shrivastava from Precog IIITH participated in the Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC-2021) shared task as a part of the CEUR workshop organized by FIRE 2021 from 13 – 17 December. The challenge was centered around hate speech and offensive content identification in English and Indo-Aryan Languages. The team made submissions to all the 6 tasks of the challenge and was ranking 3rd amongst teams that participated in all 6 tasks.
The team also submitted a paper on Battling Hateful Content in Indic Languages at HASOC-2021 describing their work (proposed architecture and design) for the same. The paper has now been accepted and will be published in the CEUR proceedings. Research work as described by the authors:
The extensive rise in consumption of online social media (OSMs) by a large number of people poses a critical problem of curbing the spread of hateful content on these platforms. With the growing usage of OSMs in multiple languages, the task of detecting and characterizing hate becomes more complex. The subtle variations of code-mixed texts along with switching scripts only add to the complexity. This paper presents a solution for the HASOC 2021 Multilingual Twitter Hate-Speech Detection challenge by team PreCog IIIT Hyderabad. We adopt a multilingual transformer based approach and describe our architecture for all 6 subtasks as part of the challenge. Out of the 6 teams that participated in all the subtasks, our submissions rank 3rd overall.
Paper Link: https://arxiv.org/pdf/2110.12780.pdf
Leader board: https://hasocfire.github.io/hasoc/2021/results.html#
Precog lab: https://precog.iiit.ac.in/
Precog is a research group at IIIT Hyderabad that studies, analyzes, and builds different aspects of social systems. The lab works on fields including Hate Speech, Legal AI, Online Social Media and Networks, NLP for Social Good, Online Privacy, and much more. It is also associated with the Center for Computational Social Science – C2S2, a new center at IIITH.