Improving Entity Linking by Modeling Latent Entity Type Information
This work addresses a specific bottleneck in entity linking for natural language processing applications, offering an incremental improvement over existing methods.
The paper tackled the problem of neural entity linking models neglecting latent entity type information, which led to incorrect entity links, by proposing a method that injects this information into entity embeddings using BERT and integrates a BERT-based similarity score. The result was a model that significantly outperformed state-of-the-art models on the AIDA-CoNLL benchmark, correcting most type errors from the baseline.
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.