Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
This work addresses storage efficiency for deployable QA systems, particularly on edge devices, but is incremental as it optimizes an existing paradigm.
The paper tackled the problem of large storage footprint in retrieve-and-read systems for open-domain question answering by proposing strategies to reduce it by up to 160x, showing that such systems can achieve better accuracy than parametric models with comparable size, making them viable for constrained environments like edge devices.
In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closed-book QA models. However, it is also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-and-read open-domain QA system by up to 160x. Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size.