mlsanityData to 7 Oct 2026

Entity Linking in 100 Languages

arXiv 2011.02690 ↗First posted 5 Nov 2020cs.CL cs.IRcited by 52

Not on the map. Why?

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.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 16; 2023: 12; 2024: 7; 2025: 2; 2026: 4.

52 papers.

Sort:

By area:

  1. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 167
  2. 2023SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialectscited by 149
  3. 2023Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entitiescited by 112
  4. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  5. 2021Multilingual Autoregressive Entity Linkingcited by 50
  6. 2021Revisiting the Primacy of English in Zero-shot Cross-lingual Transfercited by 47
  7. 2021One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrievalcited by 46
  8. 2021Relational World Knowledge Representation in Contextual Language Models: A Reviewcited by 31
  9. 2021Highly Parallel Autoregressive Entity Linking with Discriminative Correctioncited by 21
  10. 2024Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphscited by 21
  11. 2022Multi Task Learning For Zero Shot Performance Prediction of Multilingual Modelscited by 20
  12. 2022ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSDcited by 18
38 more
  1. 2023TempEL: Linking Dynamically Evolving and Newly Emerging Entitiescited by 14
  2. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  3. 2021MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Networkcited by 10
  4. 2022Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linkingcited by 10
  5. 2022Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languagescited by 10
  6. 2022TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrievalcited by 8
  7. 2023Multilingual End to End Entity Linkingcited by 8
  8. 2024Entity Linking in the Job Market Domaincited by 7
  9. 2021Multilingual Fact Linkingcited by 6
  10. 2021Survey on English Entity Linking on Wikidatacited by 6
  11. 2023Context-Gloss Augmentation for Improving Arabic Target Sense Verificationcited by 6
  12. 2023Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphscited by 6
  13. 2024MELO: An Evaluation Benchmark for Multilingual Entity Linking of Occupationscited by 6
  14. 2022EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexingcited by 5
  15. 2022XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languagescited by 4
  16. 2022Connecting a French Dictionary from the Beginning of the 20th Century to Wikidatacited by 4
  17. 2022Multilingual Event Linking to Wikidatacited by 3
  18. 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrievalcited by 3
  19. 2024What is "Typological Diversity" in NLP?cited by 3
  20. 2024Unified Examination of Entity Linking in Absence of Candidate Setscited by 3
  21. 2022Statistical and Neural Methods for Cross-lingual Entity Label Mapping in Knowledge Graphscited by 2
  22. 2022Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmarkcited by 2
  23. 2023Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddingscited by 2
  24. 2026IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscencescited by 2
  25. 2021PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguationcited by 1
  26. 2022XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languagescited by 1
  27. 2022Robust Candidate Generation for Entity Linking on Short Social Media Textscited by 1
  28. 2023EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learningcited by 1
  29. 2024Argument-Aware Approach To Event Linkingcited by 1
  30. 2025MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linkingcited by 1
  31. 2021Cross-Lingual Fine-Grained Entity Typingcited by 0
  32. 2022Building an Icelandic Entity Linking Corpuscited by 0
  33. 2022Multilingual News Location Detection using an Entity-Based Siamese Network with Semi-Supervised Contrastive Learning and Knowledge Basecited by 0
  34. 2023Hierarchical Event Groundingcited by 0
  35. 2023Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retrievercited by 0
  36. 2023MeKB-Rec: Personal Knowledge Graph Learning for Cross-Domain Recommendationcited by 0
  37. 2025Mah=an=ama: A Unique Testbed for Literary Entity Discovery and Linkingcited by 0
  38. 2026CADEL: A Corpus of Administrative Web Documents for Japanese Entity Linkingcited by 0

50 most cited of 52 All 52 (JSON)