mlsanityData to 7 Oct 2026

End-to-End Retrieval in Continuous Space

arXiv 1811.08008 ↗First posted 19 Nov 2018cs.IR cs.CL cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

Most text-based information retrieval (IR) systems index objects by words or phrases. These discrete systems have been augmented by models that use embeddings to measure similarity in continuous space. But continuous-space models are typically used just to re-rank the top candidates. We consider the problem of end-to-end continuous retrieval, where standard approximate nearest neighbor (ANN) search replaces the usual discrete inverted index, and rely entirely on distances between learned embeddings. By training simple models specifically for retrieval, with an appropriate model architecture, we improve on a discrete baseline by 8% and 26% (MAP) on two similar-question retrieval tasks. We also discuss the problem of evaluation for retrieval systems, and show how to modify existing pairwise similarity datasets for this purpose.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 6; 2023: 16; 2024: 10; 2025: 3.

46 papers.

Sort:

By area:

  1. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  2. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  3. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  4. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  5. 2022Transformer Memory as a Differentiable Search Indexcited by 242
  6. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  7. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 167
  8. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  9. 2023How Does Generative Retrieval Scale to Millions of Passages?cited by 47
  10. 2021PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modelingcited by 43
  11. 2022Contrastive language and vision learning of general fashion conceptscited by 41
  12. 2021A Statutory Article Retrieval Dataset in Frenchcited by 40
34 more
  1. 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
  2. 2021Talk, Don't Write: A Study of Direct Speech-Based Image Retrievalcited by 19
  3. 2022Exploring Dual Encoder Architectures for Question Answeringcited by 19
  4. 2021Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Visioncited by 14
  5. 2021MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Networkcited by 10
  6. 2024ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labelingcited by 10
  7. 2023Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networkscited by 9
  8. 2023SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negativescited by 9
  9. 2023UGSL: A Unified Framework for Benchmarking Graph Structure Learningcited by 9
  10. 2023LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interactioncited by 7
  11. 2024ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrievalcited by 7
  12. 2021Learning Federated Representations and Recommendations with Limited Negativescited by 6
  13. 2023Exploring the Practicality of Generative Retrieval on Dynamic Corporacited by 6
  14. 2023Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operationscited by 5
  15. 2023Revealing the Blind Spot of Sentence Encoder Evaluation by HEROScited by 5
  16. 2023Policy-Gradient Training of Language Models for Rankingcited by 5
  17. 2025Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Modelscited by 5
  18. 2022Adam: Dense Retrieval Distillation with Adaptive Dark Examplescited by 4
  19. 2023Contextualizing Argument Quality Assessment with Relevant Knowledgecited by 4
  20. 2023Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrievalcited by 4
  21. 2025Alleviating LLM-based Generative Retrieval Hallucination in Alipay Searchcited by 4
  22. 2023Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphscited by 3
  23. 2024Retrieval with Learned Similaritiescited by 3
  24. 2023Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrievalcited by 2
  25. 2024Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuningcited by 2
  26. 2024Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selectioncited by 2
  27. 2024Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domaincited by 1
  28. 2024Mamba for Scalable and Efficient Personalized Recommendationscited by 1
  29. 2023(Vector) Space is Not the Final Frontier: Product Search as Program Synthesiscited by 0
  30. 2023Improving Neural Ranking Models with Traditional IR Methodscited by 0
  31. 2023OpenMSD: Towards Multilingual Scientific Documents Similarity Measurementcited by 0
  32. 2024Multi-word Term Embeddings Improve Lexical Product Retrievalcited by 0
  33. 2024Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrievalcited by 0
  34. 2025Improving Retrieval-Augmented Neural Machine Translation with Monolingual Datacited by 0