论文标题
对监督实体链接的预处理策略的经验评估
Empirical Evaluation of Pretraining Strategies for Supervised Entity Linking
论文作者
论文摘要
在这项工作中，我们提出了一个实体链接模型，该模型将变压器体系结构与Wikipedia链接进行了大规模预处理结合。我们的模型在两个常用实体链接数据集上实现了最新的目的：Conll的96.7％，TAC-KBP的94.9％。我们提供了详细的分析，以了解哪些设计选择对于实体链接很重要，包括负面实体候选者，变压器体系结构和输入扰动的选择。最后，我们对更具挑战性的设置（例如端到端实体链接和实体链接，无需域内培训数据）提出了有希望的结果。
In this work, we present an entity linking model which combines a Transformer architecture with large scale pretraining from Wikipedia links. Our model achieves the state-of-the-art on two commonly used entity linking datasets: 96.7% on CoNLL and 94.9% on TAC-KBP. We present detailed analyses to understand what design choices are important for entity linking, including choices of negative entity candidates, Transformer architecture, and input perturbations. Lastly, we present promising results on more challenging settings such as end-to-end entity linking and entity linking without in-domain training data.
