Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability. Previous methods largely focus on the candidate retrieval stage and ignore the essential candidate ranking stage, which disambiguates among entities and makes the final linking prediction. In this paper, we propose a read-and-select (ReS) framework by modeling the main components of entity disambiguation, i.e., mention-entity matching and cross-entity comparison. First, for each candidate, the reading module leverages mention context to output mention-aware entity representations, enabling mention-entity matching. Then, in the selecting module, we frame the choice of candidates as a sequence labeling problem, and all candidate representations are fused together to enable cross-entity comparison. Our method achieves the state-of-the-art performance on the established zero-shot EL dataset ZESHEL with a 2.55\% micro-average accuracy gain, with no need for laborious multi-phase pre-training used in most of the previous work, showing the effectiveness of both mention-entity and cross-entity interaction.

翻译：零样本实体链接旨在将实体提及与未见实体对齐，以挑战模型的泛化能力。以往方法主要聚焦于候选检索阶段，忽视了关键的候选排序阶段——该阶段对候选实体进行消歧并做出最终链接预测。本文提出一种读取与选择（ReS）框架，通过对实体消歧的核心组件（即提及-实体匹配与跨实体比较）进行建模。首先，对于每个候选实体，读取模块利用提及上下文生成感知提及的实体表示，实现提及-实体匹配。随后在选择模块中，我们将候选选择任务建模为序列标注问题，通过融合所有候选表示实现跨实体比较。本方法在标准零样本实体链接数据集ZESHEL上取得了当前最优性能，微平均准确率提升2.55%，且无需多数前期工作中繁琐的多阶段预训练，验证了提及-实体交互与跨实体交互的有效性。