EntQA: Entity Linking as Question Answering
This work addresses the entity linking problem for natural language processing by introducing a novel approach that avoids reliance on mention-candidates dictionaries or weak supervision.
The paper tackles the unnatural and difficult limitation of conventional entity linking by proposing EntQA, a model that first retrieves candidate entities and then finds their mentions in the document, achieving strong results on the GERBIL benchmarking platform.
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.