# MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network

arXiv: https://arxiv.org/abs/2106.07352 · HTML: https://mlsanity.com/paper/2106.07352/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 19 of 19)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Pre-training via Paraphrasing](https://mlsanity.com/paper/2006.15020/) (2020)
- [Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://mlsanity.com/paper/1911.03814/) (2019)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Entity Linking in 100 Languages](https://mlsanity.com/paper/2011.02690/) (2020)
- [Multilingual Autoregressive Entity Linking](https://mlsanity.com/paper/2103.12528/) (2021)
- [End-to-End Retrieval in Continuous Space](https://mlsanity.com/paper/1811.08008/) (2018)
- [Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution](https://mlsanity.com/paper/1906.01753/) (2019)
- [Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension](https://mlsanity.com/paper/1804.07726/) (2018)
- [Empirical Evaluation of Pretraining Strategies for Supervised Entity Linking](https://mlsanity.com/paper/2005.14253/) (2020)
- [Entity Linking via Dual and Cross-Attention Encoders](https://mlsanity.com/paper/2004.03555/) (2020)
- [Clustering-based Inference for Biomedical Entity Linking](https://mlsanity.com/paper/2010.11253/) (2020)

## Built on by (most cited first, 10 of 10)

- [Mention Memory: incorporating textual knowledge into Transformers through entity mention attention](https://mlsanity.com/paper/2110.06176/) (2021)
- [Entity Linking and Discovery via Arborescence-based Supervised Clustering](https://mlsanity.com/paper/2109.01242/) (2021)
- [Learn to Not Link: Exploring NIL Prediction in Entity Linking](https://mlsanity.com/paper/2305.15725/) (2023)
- [EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing](https://mlsanity.com/paper/2205.12570/) (2022)
- [Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining](https://mlsanity.com/paper/2303.15311/) (2023)
- [Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input](https://mlsanity.com/paper/2404.18784/) (2024)
- [ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution](https://mlsanity.com/paper/2210.07188/) (2022)
- [Robust Candidate Generation for Entity Linking on Short Social Media Texts](https://mlsanity.com/paper/2210.07472/) (2022)
- [Named Entity Linking with Entity Representation by Multiple Embeddings](https://mlsanity.com/paper/2205.10498/) (2022)
- [When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World](https://mlsanity.com/paper/2608.23507/) (2026)

## Abstract (arXiv)

We present an instance-based nearest neighbor approach to entity linking. In contrast to most prior entity retrieval systems which represent each entity with a single vector, we build a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions of different entities. This approach allows all mentions of an entity to serve as "class prototypes" as inference involves retrieving from the full set of labeled entity mentions in the training set and applying the nearest mention neighbor's entity label. Our model is trained on a large multilingual corpus of mention pairs derived from Wikipedia hyperlinks, and performs nearest neighbor inference on an index of 700 million mentions. It is simpler to train, gives more interpretable predictions, and outperforms all other systems on two multilingual entity linking benchmarks.