https://github.com/freedomintelligence/dptdr

Code for COLING22 paper, DPTDR: Deep Prompt Tuning for Dense Passage Retrieval
https://github.com/freedomintelligence/dptdr

dense-retrieval information-retrieval p-tuning prompt-learning prompt-tuning question-answering

Last synced: about 1 year ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/freedomintelligence/dptdr
• Owner: FreedomIntelligence
• License: apache-2.0
• Created: 2022-08-25T02:46:10.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2023-08-07T23:59:46.000Z (almost 3 years ago)
• Last Synced: 2025-03-30T19:22:41.756Z (about 1 year ago)
• Topics: dense-retrieval, information-retrieval, p-tuning, prompt-learning, prompt-tuning, question-answering
• Language: Python
• Homepage:
• Size: 40 KB
• Stars: 25
• Watchers: 3
• Forks: 5
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Introduction

Code for the paper, DPTDR: Deep Prompt Tuning for Dense Passage Retrieval. We mainly develped our code based on [coCondenser](https://github.com/luyug/Dense.git) and [P-tuning v2](https://github.com/THUDM/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

```bibtex

@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}

}

```