EntQA: Entity Linking as Question Answering

TL;DR

EntQA reframes entity linking as a question answering task, using a two-stage process with candidate retrieval and document scrutiny, leveraging pretrained models to improve accuracy without extensive supervision.

Contribution

The paper introduces EntQA, a novel entity linking model that avoids traditional mention detection, combining dense retrieval and reading comprehension for improved performance.

Findings

Achieves strong results on GERBIL benchmark

Does not rely on mention-candidates dictionaries

Operates without large-scale weak supervision

Abstract

A conventional approach to entity linking is to first find mentions in a given document and then infer their underlying entities in the knowledge base. A well-known limitation of this approach is that it requires finding mentions without knowing their entities, which is unnatural and difficult. We present a new model that does not suffer from this limitation called EntQA, which stands for Entity linking as Question Answering. EntQA first proposes candidate entities with a fast retrieval module, and then scrutinizes the document to find mentions of each candidate with a powerful reader module. Our approach combines progress in entity linking with that in open-domain question answering and capitalizes on pretrained models for dense entity retrieval and reading comprehension. Unlike in previous works, we do not rely on a mention-candidates dictionary or large-scale weak supervision. EntQA achieves strong results on the GERBIL benchmarking platform.