Pruning the Index Contents for Memory Efficient Open-Domain QA

TL;DR

This paper introduces R2-D2, a pipeline for open-domain QA that efficiently prunes large indexes, reducing size significantly while maintaining high accuracy.

Contribution

It proposes a novel R2-D2 pipeline combining retriever, reranker, and readers, along with a simple index pruning method for memory-efficient QA systems.

Findings

Index size reduced to 6GiB with only 8% content retained

Achieved only 3% loss in exact match accuracy

System components fit into a small Docker image

Abstract

This work presents a novel pipeline that demonstrates what is achievable with a combined effort of state-of-the-art approaches. Specifically, it proposes the novel R2-D2 (Rank twice, reaD twice) pipeline composed of retriever, passage reranker, extractive reader, generative reader and a simple way to combine them. Furthermore, previous work often comes with a massive index of external documents that scales in the order of tens of GiB. This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library components fits into 6GiB docker image while retaining only 8% of original index contents and losing only 3% EM accuracy.