# Entity Linking in 100 Languages

arXiv: https://arxiv.org/abs/2011.02690 · HTML: https://mlsanity.com/paper/2011.02690/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 30 of 52)

- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects](https://mlsanity.com/paper/2309.07445/) (2023)
- [Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities](https://mlsanity.com/paper/2302.11154/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Multilingual Autoregressive Entity Linking](https://mlsanity.com/paper/2103.12528/) (2021)
- [Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer](https://mlsanity.com/paper/2106.16171/) (2021)
- [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://mlsanity.com/paper/2107.11976/) (2021)
- [Relational World Knowledge Representation in Contextual Language Models: A Review](https://mlsanity.com/paper/2104.05837/) (2021)
- [Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs](https://mlsanity.com/paper/2410.14057/) (2024)
- [Highly Parallel Autoregressive Entity Linking with Discriminative Correction](https://mlsanity.com/paper/2109.03792/) (2021)
- [Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models](https://mlsanity.com/paper/2205.06130/) (2022)
- [ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD](https://mlsanity.com/paper/2205.09685/) (2022)
- [TempEL: Linking Dynamically Evolving and Newly Emerging Entities](https://mlsanity.com/paper/2302.02500/) (2023)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network](https://mlsanity.com/paper/2106.07352/) (2021)
- [Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking](https://mlsanity.com/paper/2202.13404/) (2022)
- [Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages](https://mlsanity.com/paper/2205.06356/) (2022)
- [TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval](https://mlsanity.com/paper/2204.08173/) (2022)
- [Multilingual End to End Entity Linking](https://mlsanity.com/paper/2306.08896/) (2023)
- [Entity Linking in the Job Market Domain](https://mlsanity.com/paper/2401.17979/) (2024)
- [Multilingual Fact Linking](https://mlsanity.com/paper/2109.14364/) (2021)
- [Survey on English Entity Linking on Wikidata](https://mlsanity.com/paper/2112.01989/) (2021)
- [Context-Gloss Augmentation for Improving Arabic Target Sense Verification](https://mlsanity.com/paper/2302.03126/) (2023)
- [Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs](https://mlsanity.com/paper/2311.15781/) (2023)
- [MELO: An Evaluation Benchmark for Multilingual Entity Linking of Occupations](https://mlsanity.com/paper/2410.08319/) (2024)
- [EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing](https://mlsanity.com/paper/2205.12570/) (2022)
- [XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages](https://mlsanity.com/paper/2202.00291/) (2022)
- [Connecting a French Dictionary from the Beginning of the 20th Century to Wikidata](https://mlsanity.com/paper/2206.11022/) (2022)
- [Multilingual Event Linking to Wikidata](https://mlsanity.com/paper/2204.06535/) (2022)
- [Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval](https://mlsanity.com/paper/2302.01626/) (2023)

## Abstract (arXiv)

We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a single entity retrieval model that covers 100+ languages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose challenges at this large-scale, so we advocate for an increased focus on zero- and few-shot evaluation. To this end, we provide Mewsli-9, a large new multilingual dataset (http://goo.gle/mewsli-dataset) matched to our setting, and show how frequency-based analysis provided key insights for our model and training enhancements.