Skip to content

Code for COLING22 paper, DPTDR: Deep Prompt Tuning for Dense Passage Retrieval

License

Notifications You must be signed in to change notification settings

FreedomIntelligence/DPTDR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

Code for the paper, DPTDR: Deep Prompt Tuning for Dense Passage Retrieval. We mainly develped our code based on coCondenser and P-tuning v2.

Installation

For environment, please run sh install_env.sh in a clean conda environment of python>=3.7. Then just run pip install -e ..

Reproduction for MS-MARCO

Please refer to examples/msmarco-passage-ranking.

Reproduction for Natural Questions

Please refer to examples/natural-questions.

References

@article{tang2022dptdr,
  title={DPTDR: Deep Prompt Tuning for Dense Passage Retrieval},
  author={Tang, Zhengyang and Wang, Benyou and Yao, Ting},
  journal={arXiv preprint arXiv:2208.11503},
  year={2022}
}