Code Monkey home page Code Monkey logo

genret's Introduction

Learning to Tokenize for Generative Retrieval

Code of the paper Learning to Tokenize for Generative Retrieval.

Model

Environment

pytorch, transformers, accelerate, faiss, k_means_constrained

Dataset

NQ320K: unzip dataset/nq320k.zip

Other datasets coming soon.

Training and Evaluation

Code for GenRet on NQ320K:

python run.py --model_name t5-base --code_num 512 --max_length 3 --train_data dataset/nq320k/train.json --dev_data dataset/nq320k/dev.json --corpus_data dataset/nq320k/corpus_lite.json --save_path out/model

Code for generative retrieval baselines: baseline.py

Code for dense retrieval baselines: dpr.py

Cite

@article{Sun2023LearningTT,
  title={Learning to Tokenize for Generative Retrieval},
  author={Weiwei Sun and Lingyong Yan and Zheng Chen and Shuaiqiang Wang and Haichao Zhu and Pengjie Ren and Zhumin Chen and Dawei Yin and M. de Rijke and Zhaochun Ren},
  journal={ArXiv},
  year={2023},
  volume={abs/2304.04171},
}

genret's People

Contributors

sunnweiwei avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.