Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given input document and then link the mentions to corresponding entities in a specific knowledge base. Recently, the paradigm of retriever-reader promotes the progress of end-to-end EL, benefiting from the advantages of dense entity retrieval and machine reading comprehension. However, the existing study only trains the retriever and the reader separately in a pipeline manner, which ignores the benefit that the interaction between the retriever and the reader can bring to the task. To advance the retriever-reader paradigm to perform more perfectly on end-to-end EL, we propose BEER$^2$, a Bidirectional End-to-End training framework for Retriever and Reader. Through our designed bidirectional end-to-end training, BEER$^2$ guides the retriever and the reader to learn from each other, make progress together, and ultimately improve EL performance. Extensive experiments on benchmarks of multiple domains demonstrate the effectiveness of our proposed BEER$^2$.

翻译：实体链接（Entity Linking, EL）是信息抽取与知识图谱中的基础任务。通用形式的EL（即端到端EL）旨在首先在给定输入文档中发现提及，随后将提及与特定知识库中的对应实体进行链接。近年来，得益于密集实体检索与机器阅读理解的优势，检索器-阅读器范式推动了端到端EL的发展。然而，现有研究仅以流水线方式分别训练检索器与阅读器，忽略了二者间交互能为任务带来的益处。为促使检索器-阅读器范式在端到端EL中表现更优，我们提出BEER$^2$——一种面向检索器与阅读器的双向端到端训练框架。通过设计的双向端到端训练，BEER$^2$引导检索器与阅读器互相学习、共同进步，最终提升EL性能。在多个领域的基准数据集上的大量实验证明了所提出的BEER$^2$的有效性。