We present an instance-based nearest neighbor approach to entity linking. In contrast to most prior entity retrieval systems which represent each entity with a single vector, we build a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions of different entities. This approach allows all mentions of an entity to serve as "class prototypes" as inference involves retrieving from the full set of labeled entity mentions in the training set and applying the nearest mention neighbor's entity label. Our model is trained on a large multilingual corpus of mention pairs derived from Wikipedia hyperlinks, and performs nearest neighbor inference on an index of 700 million mentions. It is simpler to train, gives more interpretable predictions, and outperforms all other systems on two multilingual entity linking benchmarks.

中文翻译：

---

MOLEMAN：仅提及实体与提及注释网络的链接

我们提出了一种基于实例的最近邻实体链接方法。与使用单个向量表示每个实体的大多数先前实体检索系统相比，我们构建了一个上下文化的提及编码器，它学习将同一实体的相似提及放置在向量空间中，而不是将不同实体的提及放置得更近。这种方法允许实体的所有提及作为“类原型”，因为推理涉及从训练集中的完整标记实体提及集中检索并应用最近提及邻居的实体标签。我们的模型在源自维基百科超链接的大型多语言提及对语料库上进行训练，并在 7 亿次提及的索引上执行最近邻推理。训练更简单，提供更多可解释的预测，