# Distant Learning for Entity Linking with Automatic Noise Detection

arXiv: https://arxiv.org/abs/1905.07189 · HTML: https://mlsanity.com/paper/1905.07189/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 11 of 11)

- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking](https://mlsanity.com/paper/2101.02394/) (2021)
- [Effective Few-Shot Named Entity Linking by Meta-Learning](https://mlsanity.com/paper/2207.05280/) (2022)
- [CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning](https://mlsanity.com/paper/2411.00873/) (2024)
- [Low-Rank Subspaces for Unsupervised Entity Linking](https://mlsanity.com/paper/2104.08737/) (2021)
- [Strong Heuristics for Named Entity Linking](https://mlsanity.com/paper/2207.02824/) (2022)
- [Learning Entity Linking Features for Emerging Entities](https://mlsanity.com/paper/2208.03877/) (2022)
- [Revisiting Sparse Retrieval for Few-shot Entity Linking](https://mlsanity.com/paper/2310.12444/) (2023)
- [Domain Adaptation of Multilingual Semantic Search -- Literature Review](https://mlsanity.com/paper/2402.02932/) (2024)
- [Hybrid X-Linker: Automated Data Generation and Extreme Multi-label Ranking for Biomedical Entity Linking](https://mlsanity.com/paper/2407.06292/) (2024)
- [Query Brand Entity Linking in E-Commerce Search](https://mlsanity.com/paper/2502.01555/) (2025)

## Abstract (arXiv)

Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. As the learning signal is weak and our surrogate labels are noisy, we introduce a noise detection component in our model: it lets the model detect and disregard examples which are likely to be noisy. Our method, jointly learning to detect noise and link entities, greatly outperforms the surface matching baseline. For a subset of entity categories, it even approaches the performance of supervised learning.