论文标题
通过建模潜在实体类型信息来改善实体链接
Improving Entity Linking by Modeling Latent Entity Type Information
论文作者
论文摘要
现有的艺术神经实体链接模型的状态采用基于注意的词袋上下文模型和预训练的实体嵌入，从单词嵌入式启动，以评估主题级别上下文的兼容性。但是，在提及的直接上下文中，潜在实体类型信息被忽略了，这导致模型经常链接到不正确类型的错误实体。为了解决这个问题，我们建议将潜在实体类型信息注入基于预训练的BERT的实体嵌入中。此外，我们将基于BERT的实体相似性分数集成到最新模型的本地上下文模型中，以更好地捕获潜在实体类型信息。我们的模型极大地胜过标准基准（AIDA-CONLL）的最先进的实体链接模型。详细的实验分析表明，我们的模型纠正了直接基线产生的大多数类型误差。
Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. However, the latent entity type information in the immediate context of the mention is neglected, which causes the models often link mentions to incorrect entities with incorrect type. To tackle this problem, we propose to inject latent entity type information into the entity embeddings based on pre-trained BERT. In addition, we integrate a BERT-based entity similarity score into the local context model of a state-of-the-art model to better capture latent entity type information. Our model significantly outperforms the state-of-the-art entity linking models on standard benchmark (AIDA-CoNLL). Detailed experiment analysis demonstrates that our model corrects most of the type errors produced by the direct baseline.
