EntQA: Entity Linking as Question Answering

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.

Building Chinese interdisciplinary research centers : the case of Tsinghua University

“…Retrieval-based NLP For many NLP tasks [Li et al, 2023a[Li et al, , 2022c, retrieval is an effective method to utilize external knowledge. Knowledge retrieval has been utilized in a variety of NLP tasks [Li et al, 2022b;Li et al, 2022a;], including question answering [Xu et al, 2022;Wang et al, 2022a], machine translation Xu et al, 2020], NER Wang et al, 2022b], and entity linking [Zhang et al, 2021;Li et al, 2023b]. Recently, knowledge retrieval has been introduced to language model pretraining.…”