T.M. Scanlon at SemEval-2023 Task 4: Leveraging Pretrained Language Models for Human Value Argument Mining with Contrastive Learning

Milad Molazadeh Oskuee, Mostafa Rahgouy, Hamed Babaei Giglou, Cheryl D Seals


Abstract
Human values are of great concern to social sciences which refer to when people have different beliefs and priorities of what is generally worth striving for and how to do so. This paper presents an approach for human value argument mining using contrastive learning to leverage the isotropy of language models. We fine-tuned DeBERTa-Large in a multi-label classification fashion and achieved an F1 score of 49% for the task, resulting in a rank of 11. Our proposed model provides a valuable tool for analyzing arguments related to human values and highlights the significance of leveraging the isotropy of large language models for identifying human values.
Anthology ID:
2023.semeval-1.82
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
603–608
Language:
URL:
https://aclanthology.org/2023.semeval-1.82
DOI:
10.18653/v1/2023.semeval-1.82
Bibkey:
Cite (ACL):
Milad Molazadeh Oskuee, Mostafa Rahgouy, Hamed Babaei Giglou, and Cheryl D Seals. 2023. T.M. Scanlon at SemEval-2023 Task 4: Leveraging Pretrained Language Models for Human Value Argument Mining with Contrastive Learning. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 603–608, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
T.M. Scanlon at SemEval-2023 Task 4: Leveraging Pretrained Language Models for Human Value Argument Mining with Contrastive Learning (Molazadeh Oskuee et al., SemEval 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.semeval-1.82.pdf