Abstract
In this paper, we initially discuss about the ValueEval task and the challenges involved in multi-label classification tasks. We tried to approach this task using Natural Language Inference and proposed a Grouped-BERT architecture which leverages commonality between the classes for a multi-label classification tasks.- Anthology ID:
- 2023.semeval-1.222
- 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:
- 1609–1612
- Language:
- URL:
- https://aclanthology.org/2023.semeval-1.222
- DOI:
- 10.18653/v1/2023.semeval-1.222
- Cite (ACL):
- Ajay Narasimha Mopidevi and Hemanth Chenna. 2023. Quintilian at SemEval-2023 Task 4: Grouped BERT for Multi-Label Classification. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1609–1612, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Quintilian at SemEval-2023 Task 4: Grouped BERT for Multi-Label Classification (Mopidevi & Chenna, SemEval 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.semeval-1.222.pdf