Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

TL;DR

This survey comprehensively reviews recent advancements in open-domain question answering, focusing on neural machine reading comprehension techniques, system architectures, challenges, and benchmark analyses to guide future research.

Contribution

It provides a detailed overview of modern OpenQA systems, especially the Retriever-Reader architecture, and discusses key challenges and benchmarks in the field.

Findings

Neural MRC techniques have significantly improved OpenQA performance.

The Retriever-Reader architecture is a prevalent framework in recent systems.

Benchmark datasets are crucial for evaluating OpenQA advancements.

Abstract

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a surge in the amount of research literature on OpenQA, particularly on techniques that integrate with neural Machine Reading Comprehension (MRC). While these research works have advanced performance to new heights on benchmark datasets, they have been rarely covered in existing surveys on QA systems. In this work, we review the latest research trends in OpenQA, with particular attention to systems that incorporate neural MRC techniques. Specifically, we begin with revisiting the origin and development of OpenQA systems. We then introduce modern OpenQA architecture named "Retriever-Reader" and analyze the various systems that follow this architecture as well as the specific techniques adopted in each of the components. We then discuss key challenges to developing OpenQA systems and offer an analysis of benchmarks that are commonly used. We hope our work would enable researchers to be informed of the recent advancement and also the open challenges in OpenQA research, so as to stimulate further progress in this field.