# Proxy-based Zero-Shot Entity Linking by Effective Candidate Retrieval

arXiv: https://arxiv.org/abs/2301.13318 · HTML: https://mlsanity.com/paper/2301.13318/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [End-to-End Neural Entity Linking](https://mlsanity.com/paper/1808.07699/) (2018)
- [Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://mlsanity.com/paper/1911.03814/) (2019)
- [MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts](https://mlsanity.com/paper/1902.09476/) (2019)
- [Neural Entity Linking: A Survey of Models Based on Deep Learning](https://mlsanity.com/paper/2006.00575/) (2020)
- [Understanding Hard Negatives in Noise Contrastive Estimation](https://mlsanity.com/paper/2104.06245/) (2021)
- [Improved Text Classification via Contrastive Adversarial Training](https://mlsanity.com/paper/2107.10137/) (2021)
- [Fast and Effective Biomedical Entity Linking Using a Dual Encoder](https://mlsanity.com/paper/2103.05028/) (2021)
- [Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text](https://mlsanity.com/paper/2110.08228/) (2021)
- [MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations](https://mlsanity.com/paper/2109.05716/) (2021)

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

- [Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever](https://mlsanity.com/paper/2308.03365/) (2023)
- [HNSW with Accuracy Guarantees Using Graph Spanners](https://mlsanity.com/paper/2607.02338/) (2026)

## Abstract (arXiv)

A recent advancement in the domain of biomedical Entity Linking is the development of powerful two-stage algorithms, an initial candidate retrieval stage that generates a shortlist of entities for each mention, followed by a candidate ranking stage. However, the effectiveness of both stages are inextricably dependent on computationally expensive components. Specifically, in candidate retrieval via dense representation retrieval it is important to have hard negative samples, which require repeated forward passes and nearest neighbour searches across the entire entity label set throughout training. In this work, we show that pairing a proxy-based metric learning loss with an adversarial regularizer provides an efficient alternative to hard negative sampling in the candidate retrieval stage. In particular, we show competitive performance on the recall@1 metric, thereby providing the option to leave out the expensive candidate ranking step. Finally, we demonstrate how the model can be used in a zero-shot setting to discover out of knowledge base biomedical entities.