TL;DR We’ve released (a while ago, now, with no further report of any major issues, warranting this blog post!) rerankers, a low-dependency Python library to provide a unified interface to all commonly used re-ranking models. It’s available on GitHub here. In this post, we quickly discuss: Why two-stage pipelines are so popular, and how they’re born of various trade-offs. The various methods now commonly used in re-ranking. rerankers itself, its design philosophy and how to use it. Intr...
