Is Retriever Merely an Approximator of Reader?

TL;DR

This paper investigates the relationship between retrievers and readers in open-domain QA, showing they are complementary and proposing a distillation method to improve retriever performance and robustness.

Contribution

It demonstrates that retrievers and readers are not just approximators but complementary, and introduces a distillation approach to enhance retriever accuracy and robustness.

Findings

Reader and retriever are complementary in accuracy.

Distillation improves retriever recall and QA accuracy.

Method enhances off-the-shelf retrievers in open-domain QA.

Abstract

The state of the art in open-domain question answering (QA) relies on an efficient retriever that drastically reduces the search space for the expensive reader. A rather overlooked question in the community is the relationship between the retriever and the reader, and in particular, if the whole purpose of the retriever is just a fast approximation for the reader. Our empirical evidence indicates that the answer is no, and that the reader and the retriever are complementary to each other even in terms of accuracy only. We make a careful conjecture that the architectural constraint of the retriever, which has been originally intended for enabling approximate search, seems to also make the model more robust in large-scale search. We then propose to distill the reader into the retriever so that the retriever absorbs the strength of the reader while keeping its own benefit. Experimental results show that our method can enhance the document recall rate as well as the end-to-end QA accuracy of off-the-shelf retrievers in open-domain QA tasks.