# Improving Entity Linking by Modeling Latent Entity Type Information

arXiv: https://arxiv.org/abs/2001.01447 · HTML: https://mlsanity.com/paper/2001.01447/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2020.

## Built on by (most cited first, 18 of 18)

- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.10368/) (2023)
- [Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking](https://mlsanity.com/paper/2101.02394/) (2021)
- [Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation](https://mlsanity.com/paper/2206.13746/) (2022)
- [TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval](https://mlsanity.com/paper/2204.08173/) (2022)
- [A Review of Knowledge Graph Completion](https://mlsanity.com/paper/2208.11652/) (2022)
- [Improving Zero-Shot Entity Retrieval through Effective Dense Representations](https://mlsanity.com/paper/2103.04156/) (2021)
- [OKGIT: Open Knowledge Graph Link Prediction with Implicit Types](https://mlsanity.com/paper/2106.12806/) (2021)
- [The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing](https://mlsanity.com/paper/2404.08313/) (2024)
- [DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking](https://mlsanity.com/paper/2209.13187/) (2022)
- [Ontology Enrichment for Effective Fine-grained Entity Typing](https://mlsanity.com/paper/2310.07795/) (2023)
- [Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings](https://mlsanity.com/paper/2305.12027/) (2023)
- [Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision](https://mlsanity.com/paper/2109.09036/) (2021)
- [Learning to Select the Next Reasonable Mention for Entity Linking](https://mlsanity.com/paper/2112.04104/) (2021)
- [End-to-End Entity Detection with Proposer and Regressor](https://mlsanity.com/paper/2210.10260/) (2022)
- [Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuning](https://mlsanity.com/paper/2310.14596/) (2023)
- [M3EL: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking](https://mlsanity.com/paper/2410.18096/) (2024)
- [PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking](https://mlsanity.com/paper/2510.02726/) (2025)

## Abstract (arXiv)

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.