Pruning the Index Contents for Memory Efficient Open-Domain QA
This addresses the problem of high memory usage for researchers and practitioners in open-domain QA, though it is incremental as it builds on existing state-of-the-art approaches.
The paper tackles memory inefficiency in open-domain QA systems by proposing a pipeline that prunes index contents, reducing the system to a 6GiB docker image with only 8% of the original index while losing only 3% EM accuracy.
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.