End-to-End Training of Neural Retrievers for Open-Domain Question Answering

TL;DR

This paper introduces an effective unsupervised pre-training method for neural retrievers in open-domain QA, combined with end-to-end supervised training, achieving state-of-the-art results on major datasets.

Contribution

It presents a novel combination of unsupervised pre-training and end-to-end supervised training for neural retrievers in open-domain QA, improving retrieval accuracy and answer extraction performance.

Findings

Achieved 84% top-20 retrieval accuracy on Natural Questions.

Outperformed recent models like DPR, REALM, and RAG in answer extraction.

Demonstrated scalability with larger models leading to consistent performance gains.

Abstract

Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised approaches. However, it remains unclear how unsupervised and supervised methods can be used most effectively for neural retrievers. In this work, we systematically study retriever pre-training. We first propose an approach of unsupervised pre-training with the Inverse Cloze Task and masked salient spans, followed by supervised finetuning using question-context pairs. This approach leads to absolute gains of 2+ points over the previous best result in the top-20 retrieval accuracy on Natural Questions and TriviaQA datasets. We also explore two approaches for end-to-end supervised training of the reader and retriever components in OpenQA models. In the first approach, the reader considers each retrieved document separately while in the second approach, the reader considers all the retrieved documents together. Our experiments demonstrate the effectiveness of these approaches as we obtain new state-of-the-art results. On the Natural Questions dataset, we obtain a top-20 retrieval accuracy of 84, an improvement of 5 points over the recent DPR model. In addition, we achieve good results on answer extraction, outperforming recent models like REALM and RAG by 3+ points. We further scale up end-to-end training to large models and show consistent gains in performance over smaller models.