Unsupervised Open-Domain Question Answering

TL;DR

This paper introduces the first approach to unsupervised open-domain question answering, proposing data construction methods that enable the task to reach up to 86% of supervised performance.

Contribution

It pioneers the task of unsupervised ODQA and develops key data construction techniques to facilitate its development.

Findings

Unsupervised ODQA can achieve up to 86% of supervised performance.

Proposed data construction methods are effective for unsupervised ODQA.

First formal introduction of unsupervised ODQA in the literature.

Abstract

Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner. However, data annotation cannot also be irresistible for its huge demand in an open domain. Though unsupervised QA or unsupervised Machine Reading Comprehension (MRC) has been tried more or less, unsupervised ODQA has not been touched according to our best knowledge. This paper thus pioneers the work of unsupervised ODQA by formally introducing the task and proposing a series of key data construction methods. Our exploration in this work inspiringly shows unsupervised ODQA can reach up to 86% performance of supervised ones.