Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encoders
- Anthology ID:
- 2023.sustainlp-1.4
- Volume:
- Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada (Hybrid)
- Editors:
- Nafise Sadat Moosavi, Iryna Gurevych, Yufang Hou, Gyuwan Kim, Young Jin Kim, Tal Schuster, Ameeta Agrawal
- Venue:
- sustainlp
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 59–77
- Language:
- URL:
- https://aclanthology.org/2023.sustainlp-1.4
- DOI:
- 10.18653/v1/2023.sustainlp-1.4
- Cite (ACL):
- Daniel Campos, Alessandro Magnani, and Chengxiang Zhai. 2023. Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encoders. In Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 59–77, Toronto, Canada (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encoders (Campos et al., sustainlp 2023)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2023.sustainlp-1.4.pdf