Skip to content
@castorini

Castorini

Deep learning for natural language processing and information retrieval at the University of Waterloo

Pinned

  1. anserini Public

    Anserini is a Lucene toolkit for reproducible information retrieval research

    Java 796 297

  2. pyserini Public

    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

    Python 718 200

  3. pygaggle Public

    a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini

    Jupyter Notebook 223 90

  4. covidex Public

    A multi-stage neural search engine for the COVID-19 Open Research Dataset

    TypeScript 133 29

  5. honk Public

    PyTorch implementations of neural network models for keyword spotting

    Python 475 121

  6. hedwig Public

    PyTorch deep learning models for document classification

    Python 534 122

Repositories

  • afriteva Public

    Text - 2 - Text for African languages

    Python 4 1 0 1 Updated Jan 11, 2023
  • anserini Public

    Anserini is a Lucene toolkit for reproducible information retrieval research

    Java 796 Apache-2.0 297 18 4 Updated Jan 11, 2023
  • pyserini Public

    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

    Python 718 Apache-2.0 200 32 10 Updated Jan 11, 2023
  • pygaggle Public

    a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini

    Jupyter Notebook 223 Apache-2.0 90 16 24 Updated Jan 7, 2023
  • anserini-tools Public

    Evaluation tools shared across anserini, pyserini, and pygaggle

    Python 12 13 1 0 Updated Jan 7, 2023
  • covidex Public

    A multi-stage neural search engine for the COVID-19 Open Research Dataset

    TypeScript 133 MIT 29 10 23 Updated Jan 6, 2023
  • daam Public

    Diffusion attentive attribution maps for interpreting Stable Diffusion.

    Python 229 MIT 18 6 0 Updated Dec 16, 2022
  • d-bert Public

    Distilling BERT using natural language generation.

    Python 29 MIT 13 0 0 Updated Dec 16, 2022
  • africlirmatrix Public

    AfriCLIRMatrix is a test collection for cross-lingual information retrieval research in 15 diverse African languages.

    1 Apache-2.0 1 0 0 Updated Dec 10, 2022
  • honkling Public

    Web app for keyword spotting using TensorflowJS

    JavaScript 65 MIT 11 1 11 Updated Dec 8, 2022

Top languages

Loading…

Most used topics

Loading…