NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914737093083136 |
|---|---|
| author | Wang, Jingyuan Xu, Shengdong Yang, Yang |
| author_facet | Wang, Jingyuan Xu, Shengdong Yang, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19713 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification Wang, Jingyuan Xu, Shengdong Yang, Yang Computation and Language Machine Learning 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. |
| title | NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2403.19713 |