# Learning Entity Linking Features for Emerging Entities

arXiv: https://arxiv.org/abs/2208.03877 · HTML: https://mlsanity.com/paper/2208.03877/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 8 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [Deep Joint Entity Disambiguation with Local Neural Attention](https://mlsanity.com/paper/1704.04920/) (2017)
- [Efficient One-Pass End-to-End Entity Linking for Questions](https://mlsanity.com/paper/2010.02413/) (2020)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://mlsanity.com/paper/1601.01343/) (2016)
- [Neural Entity Linking: A Survey of Models Based on Deep Learning](https://mlsanity.com/paper/2006.00575/) (2020)
- [Jointly Learning Explainable Rules for Recommendation with Knowledge Graph](https://mlsanity.com/paper/1903.03714/) (2019)
- [Joint Entity Linking with Deep Reinforcement Learning](https://mlsanity.com/paper/1902.00330/) (2019)
- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [Neural Collective Entity Linking](https://mlsanity.com/paper/1811.08603/) (2018)
- [Boosting Entity Linking Performance by Leveraging Unlabeled Documents](https://mlsanity.com/paper/1906.01250/) (2019)
- [Distant Learning for Entity Linking with Automatic Noise Detection](https://mlsanity.com/paper/1905.07189/) (2019)
- [Pair-Linking for Collective Entity Disambiguation: Two Could Be Better Than All](https://mlsanity.com/paper/1802.01074/) (2018)
- [Discovering Entities with Just a Little Help from You](https://mlsanity.com/paper/1810.10252/) (2018)
- [Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning](https://mlsanity.com/paper/1906.09320/) (2019)
- [How much is Wikipedia Lagging Behind News?](https://mlsanity.com/paper/1703.10345/) (2017)

## Built on by (most cited first, 2 of 2)

- [Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking](https://mlsanity.com/paper/2306.12245/) (2023)
- [Hybrid X-Linker: Automated Data Generation and Extreme Multi-label Ranking for Biomedical Entity Linking](https://mlsanity.com/paper/2407.06292/) (2024)

## Abstract (arXiv)

Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL models will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.