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：摘要：实体链接是信息抽取和知识图谱中的一项基础任务。通用形式的实体链接（即端到端实体链接）旨在首先在给定输入文档中发现提及，然后将这些提及链接到特定知识库中的对应实体。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实体链接的进展。然而，现有研究仅以流水线方式分别训练检索器和阅读器，忽视了检索器与阅读器之间的交互能为该任务带来的益处。为使检索器-阅读器范式在端到端实体链接中表现更完善，我们提出BEER$^2$——一种面向检索器和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$^2$引导检索器和阅读器相互学习、共同进步，最终提升实体链接性能。多领域基准数据集上的大量实验证明了所提BEER$^2$的有效性。