Fast-Forward Indexes

Fast-Forward indexes combine the efficiency of lexical sparse retrieval methods with the effectiveness of semantic dense retrieval methods. Our approach outperforms both sparse (e.g. BM25) and dense (e.g. TCT-ColBERT) retrievers and is more efficient than dense retrieval.

pip install fast-forward-indexes

API | GitHub | PyPI

Ranking Models

This repository contains the implementations of our ranking models as well as some baselines. It supports training, validation, testing and re-ranking.


Ranking Utilities

This library provides utilities for training ranking models, offering integration with PyTorch Lightning.


© 2022 Jurek Leonhardt

Made with TEA Stack, 11ty, tailwindcss, Alpine.js and Font Awesome

Datenschutz Impressum