Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of corresponding context from the Pre-trained Language Model. However, we argue that such coarse-grained sentence embeddings can not fully model the mentions/entities, especially when the attention scores towards mentions/entities are relatively low. In this work, we propose GER, a \textbf{G}raph enhanced \textbf{E}ntity \textbf{R}etrieval framework, to capture more fine-grained information as complementary to sentence embeddings. We extract the knowledge units from the corresponding context and then construct a mention/entity centralized graph. Hence, we can learn the fine-grained information about mention/entity by aggregating information from these knowledge units. To avoid the graph information bottleneck for the central mention/entity node, we construct a hierarchical graph and design a novel Hierarchical Graph Attention Network~(HGAN). Experimental results on popular benchmarks demonstrate that our proposed GER framework performs better than previous state-of-the-art models. The code has been available at https://github.com/wutaiqiang/GER-WSDM2023.

翻译：“零点”实体检索,目的是在零点设置下与候选实体挂钩,对于自然语言处理中的许多任务至关重要。大多数现有方法都通过培训前语言模式的相应内容嵌入句子,提及/实体。然而,我们争辩说,这种粗粗化的句子嵌入无法完全模拟提及/实体,特别是当对提及/实体的关注分数相对较低时。在这项工作中,我们建议GER, 一种\ textbf{G}raph 增强的\ textbf{E}nity\ textbf{R}etrieval 框架, 捕捉取更精细精细的信息,作为判决嵌入的补充。我们从相应的背景中提取知识单位,然后构建一个提及/实体集中图表。因此,我们可以通过汇总这些知识单位的信息,学习关于提及/实体的精细度信息。为避免中央提及/entity node的图形信息瓶颈,我们制作了一个等级图表,并设计了一个新型的“高层次关注网络 ” (HAR-AN) 框架,我们从对应的用户标数框架展示了我们先前的版本。