Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

TL;DR

This paper presents DistDR, a distantly-supervised evidence retrieval method that improves question answering performance without requiring evidence annotations, matching state-of-the-art results.

Contribution

Introduces DistDR, a novel iterative evidence retrieval approach that learns from answer labels alone, eliminating the need for costly evidence annotations.

Findings

DistDR achieves comparable performance to fully-supervised methods.

Iterative evidence refinement improves retrieval accuracy.

Model effectively learns evidence retrieval from answer supervision alone.

Abstract

Open-domain question answering answers a question based on evidence retrieved from a large corpus. State-of-the-art neural approaches require intermediate evidence annotations for training. However, such intermediate annotations are expensive, and methods that rely on them cannot transfer to the more common setting, where only question-answer pairs are available. This paper investigates whether models can learn to find evidence from a large corpus, with only distant supervision from answer labels for model training, thereby generating no additional annotation cost. We introduce a novel approach (DistDR) that iteratively improves over a weak retriever by alternately finding evidence from the up-to-date model and encouraging the model to learn the most likely evidence. Without using any evidence labels, DistDR is on par with fully-supervised state-of-the-art methods on both multi-hop and single-hop QA benchmarks. Our analysis confirms that DistDR finds more accurate evidence over iterations, which leads to model improvements.