Papers › Improving Entity Linking by Modeling Latent Entity Type Information

Improving Entity Linking by Modeling Latent Entity Type Information

6 Jan 2020arXiv:2001.01447archive 2025-07-28

Shuang Chen, Jinpeng Wang, Feng Jiang, Chin-Yew Lin

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.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity Disambiguation Entity Embeddings Entity Linking Vocal Bursts Type Prediction Word Embeddings

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Entity Disambiguation	AIDA-CoNLL	Chen et al. (2020) (et al, 2020)	In-KB Accuracy	93.54	#9 of 20	Archive leaderboard	report
Entity Disambiguation	AIDA-CoNLL	BERT-Entity-Sim (local & global) AIDA-B	Micro-F1	93.54	#20 of 20	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections