Training a Ranking Function for Open-Domain Question Answering

TL;DR

This paper introduces two neural network rankers designed to improve passage retrieval in open-domain question answering by scoring passages based on their likelihood of containing the answer, enhancing retrieval accuracy.

Contribution

The study proposes novel neural ranking models and analyzes the roles of semantic similarity and relevance matching in open-domain QA systems.

Findings

Neural rankers effectively identify relevant passages containing answers.

Semantic similarity and relevance matching are both important for passage ranking.

The models outperform baseline retrieval methods in open-domain QA tasks.

Abstract

In recent years, there have been amazing advances in deep learning methods for machine reading. In machine reading, the machine reader has to extract the answer from the given ground truth paragraph. Recently, the state-of-the-art machine reading models achieve human level performance in SQuAD which is a reading comprehension-style question answering (QA) task. The success of machine reading has inspired researchers to combine information retrieval with machine reading to tackle open-domain QA. However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question. In this study, we propose two neural network rankers that assign scores to different passages based on their likelihood of containing the answer to a given question. Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.