mlsanityData to 7 Oct 2026

Learning Dense Representations for Entity Retrieval

arXiv 1909.10506 ↗First posted 23 Sep 2019cs.CL cs.IR cs.LGcited by 122

Not on the map. Why?

Abstract (arXiv)

We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 26; 2023: 27; 2024: 19; 2025: 11; 2026: 6.

122 papers.

Sort:

By area:

  1. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  2. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  3. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  4. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  5. 2023Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunitiescited by 129
  6. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  7. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  8. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  9. 2021PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrievalcited by 50
  10. 2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
  11. 2021One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrievalcited by 46
  12. 2021Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedbackcited by 45
38 more
  1. 2021LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrievalcited by 44
  2. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  3. 2021Understanding Hard Negatives in Noise Contrastive Estimationcited by 39
  4. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  5. 2024jina-clip-v2: Multilingual Multimodal Embeddings for Text and Imagescited by 36
  6. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  7. 2021EntQA: Entity Linking as Question Answeringcited by 34
  8. 2021Knowledge-Rich Self-Supervision for Biomedical Entity Linkingcited by 31
  9. 2023ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrievalcited by 26
  10. 2022LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrievalcited by 24
  11. 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
  12. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  13. 2021Entity Linking and Discovery via Arborescence-based Supervised Clusteringcited by 22
  14. 2021Entity Linking Meets Deep Learning: Techniques and Solutionscited by 21
  15. 2024Corpus Poisoning via Approximate Greedy Gradient Descentcited by 21
  16. 2022Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Searchcited by 17
  17. 2022Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddingscited by 17
  18. 2022Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQAcited by 17
  19. 2021Fast and Effective Biomedical Entity Linking Using a Dual Encodercited by 16
  20. 2021Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreferencecited by 16
  21. 2021Distilling Relation Embeddings from Pre-trained Language Modelscited by 15
  22. 2021Read, Retrospect, Select: An MRC Framework to Short Text Entity Linkingcited by 14
  23. 2021BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networkscited by 14
  24. 2024Does Negative Sampling Matter? A Review with Insights into its Theory and Applicationscited by 14
  25. 2021DOCENT: Learning Self-Supervised Entity Representations from Large Document Collectionscited by 13
  26. 2021QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extractioncited by 13
  27. 2022RedHOT: A Corpus of Annotated Medical Questions, Experiences, and Claims on Social Mediacited by 13
  28. 2021Contrastive Fine-tuning Improves Robustness for Neural Rankerscited by 12
  29. 2021LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linkingcited by 11
  30. 2023Synergistic Interplay between Search and Large Language Models for Information Retrievalcited by 11
  31. 2023SpEL: Structured Prediction for Entity Linkingcited by 11
  32. 2021MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Networkcited by 10
  33. 2022Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linkingcited by 10
  34. 2023Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Modelscited by 10
  35. 2024Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transportcited by 10
  36. 2021Deep Indexed Active Learning for Matching Heterogeneous Entity Representationscited by 9
  37. 2021MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representationscited by 9
  38. 2022Modelling Commonsense Properties using Pre-Trained Bi-Encoderscited by 9

50 most cited of 122 All 122 (JSON)