Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encoders

Daniel Campos, Alessandro Magnani, Chengxiang Zhai


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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2023.sustainlp-1.4.pdf
Video:
 https://aclanthology.org/2023.sustainlp-1.4.mp4