Named Entity Linking on Namesakes

We propose a simple and practical method of named entity linking (NEL), and explore its features and performance on a dataset of ambiguous named entities - Namesakes. We represent knowledge base (KB) entity by a set of embeddings. Our observations suggest that it is reasonable to keep a limited number of such embeddings, and that the number of mentions required to create a KB entity is important. We show that representations of entities in the knowledge base (KB) can be adjusted using only KB data, and the adjustment improves NEL performance.