oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes
Daniel Campos, Alexandre Marques, Mark Kurtz, Cheng Xiang Zhai
- Anthology ID:
- 2023.sustainlp-1.3
- Volume:
- Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada (Hybrid)
- Venue:
- sustainlp
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 39–58
- Language:
- URL:
- https://aclanthology.org/2023.sustainlp-1.3
- DOI:
- Cite (ACL):
- Daniel Campos, Alexandre Marques, Mark Kurtz, and Cheng Xiang Zhai. 2023. oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes. In Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 39–58, Toronto, Canada (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes (Campos et al., sustainlp 2023)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2023.sustainlp-1.3.pdf