Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering


In open-domain question answering, retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to parametric approaches. 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 realistic 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 a comparable docker-level system size.

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics