Distilling Knowledge from Reader to Retriever for Question Answering

TL;DR

This paper introduces a knowledge distillation-based method to train retriever models for question answering without needing annotated query-document pairs, leading to improved retrieval performance.

Contribution

It proposes a novel approach that uses reader attention scores to generate synthetic labels for training retrievers, eliminating the need for supervised query-document data.

Findings

Achieved state-of-the-art results on question answering tasks.

Demonstrated effectiveness of synthetic labels derived from reader attention.

Improved retrieval accuracy without annotated training pairs.

Abstract

The task of information retrieval is an important component of many natural language processing systems, such as open domain question answering. While traditional methods were based on hand-crafted features, continuous representations based on neural networks recently obtained competitive results. A challenge of using such methods is to obtain supervised data to train the retriever model, corresponding to pairs of query and support documents. In this paper, we propose a technique to learn retriever models for downstream tasks, inspired by knowledge distillation, and which does not require annotated pairs of query and documents. Our approach leverages attention scores of a reader model, used to solve the task based on retrieved documents, to obtain synthetic labels for the retriever. We evaluate our method on question answering, obtaining state-of-the-art results.