CLTL@HarmPot-ID: Leveraging Transformer Models for Detecting Offline Harm Potential and Its Targets in Low-Resource Languages

Yeshan Wang, Ilia Markov

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

We present the winning approach to the TRAC 2024 Shared Task on Offline Harm Potential Identification (HarmPot-ID). The task focused on low-resource Indian languages and consisted of two sub-tasks: 1a) predicting the offline harm potential and 1b) detecting the most likely target(s) of the offline harm. We explored low-source domain specific, cross-lingual, and monolingual transformer models and submitted the aggregate predictions from the MuRIL and BERT models. Our approach achieved 0.74 micro-averaged F1-score for sub-task 1a and 0.96 for sub-task 1b, securing the 1st rank for both sub-tasks in the competition.

Original languageEnglish
Title of host publicationProceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024
Subtitle of host publication[TRAC-2024 Workshop]
EditorsRitesh Kumar, Atul Kr. Ojha, Atul Kr. Ojha, Shervin Malmasi, Bharathi Raja Chakravarthi, Bornini Lahiri, Siddharth Singh, Shyam Ratan
PublisherACL Anthology
Pages21-26
Number of pages6
ISBN (Electronic)9782493814470
Publication statusPublished - 2024
Event4th Workshop on Threat, Aggression and Cyberbullying, TRAC 2024 - Torino, Italy
Duration: 20 May 2024 → …

Publication series

NameTRAC 2024: 4th Workshop on Threat, Aggression and Cyberbullying at LREC-COLING 2024 - Workshop Proceedings

Conference

Conference4th Workshop on Threat, Aggression and Cyberbullying, TRAC 2024
Country/TerritoryItaly
CityTorino
Period20/05/24 → …

Bibliographical note

Publisher Copyright:
© 2024 ELRA Language Resource Association.

Fingerprint

Dive into the research topics of 'CLTL@HarmPot-ID: Leveraging Transformer Models for Detecting Offline Harm Potential and Its Targets in Low-Resource Languages'. Together they form a unique fingerprint.

Cite this