Abstract
This report provide a detailed description of the method that we proposed in the TRAC-2024 Offline Harm Potential dentification which encloses two sub-tasks. The investigation utilized a rich dataset comprised of social media comments in several Indian languages, annotated with precision by expert judges to capture the nuanced implications for offline context harm. The objective assigned to the participants was to design algorithms capable of accurately assessing the likelihood of harm in given situations and identifying the most likely target(s) of offline harm. Our approach ranked second in two separate tracks, with F1 values of 0.73 and 0.96 respectively. Our method principally involved selecting pretrained models for finetuning, incorporating contrastive learning techniques, and culminating in an ensemble approach for the test set.- Anthology ID:
- 2024.trac-1.4
- Volume:
- Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Ritesh Kumar, Atul Kr. Ojha, Shervin Malmasi, Bharathi Raja Chakravarthi, Bornini Lahiri, Siddharth Singh, Shyam Ratan
- Venues:
- TRAC | WS
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 27–31
- Language:
- URL:
- https://aclanthology.org/2024.trac-1.4
- DOI:
- Cite (ACL):
- Jingyuan Wang, Jack Depp, and Yang Yang. 2024. NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification. In Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024, pages 27–31, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification (Wang et al., TRAC-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.trac-1.4.pdf