Information Retrieval & Search

Dense/sparse retrieval, passage ranking, search embeddings, open-domain QA retrieval.

A topic in the Science corpus, drawn from 952 papers.

Trusted voices in Information Retrieval & Search

Ordered by the trust Information Retrieval & Search's own network concentrates on each researcher, most first.

  1. George A. Miller — trusted by 1,051 researchers here
  2. Thorsten Joachims — trusted by 559 researchers here
  3. Yehuda Koren — trusted by 558 researchers here
  4. W. Bruce Croft — trusted by 343 researchers here
  5. Piotr Indyk — trusted by 369 researchers here
  6. Herv'e J'egou — trusted by 298 researchers here
  7. Stephen E. Robertson — trusted by 300 researchers here
  8. Thomas Hofmann — trusted by 227 researchers here
  9. Moses Charikar — trusted by 235 researchers here
  10. Rajeev Motwani — trusted by 364 researchers here
  11. Gerard A. Salton — trusted by 298 researchers here
  12. Ellen M. Voorhees — trusted by 232 researchers here

Most-cited papers in Information Retrieval & Search

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020, Neural Information Processing Systems) — 16,110 citations
  2. An Introduction to Information Retrieval (2013) — 13,391 citations
  3. Matrix Factorization Techniques for Recommender Systems (2009) — 10,960 citations
  4. Dense Passage Retrieval for Open-Domain Question Answering (2020, Conference on Empirical Methods in Natural Language Processing) — 6,334 citations
  5. The Probabilistic Relevance Framework: BM25 and Beyond (2009) — 5,679 citations
  6. Cumulated gain-based evaluation of IR techniques (2002) — 5,590 citations
  7. Biopython: freely available Python tools for computational molecular biology and bioinformatics (2009) — 5,571 citations
  8. A statistical interpretation of term specificity and its application in retrieval (2021) — 5,376 citations
  9. Approximate Nearest Neighbor: Towards Removing the Curse of Dimensionality (2012) — 4,956 citations
  10. Natural Questions: A Benchmark for Question Answering Research (2019) — 4,925 citations
  11. YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia (2007) — 4,714 citations
  12. Optimizing search engines using clickthrough data (2002) — 4,680 citations
  13. A 20th Anniversary Survey: Introduction to 'Content-Based Image Retrieval at the End of the Early Years' (2000) — 4,535 citations
  14. Factorization meets the neighborhood: a multifaceted collaborative filtering model (2008) — 4,350 citations
  15. TextRank: Bringing Order into Text (2004) — 4,299 citations
  16. Detecting influenza epidemics using search engine query data (2009) — 4,144 citations
  17. eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses (2018) — 4,095 citations
  18. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension (2017) — 4,054 citations
  19. Image retrieval: Ideas, influences, and trends of the new age (2008) — 3,871 citations
  20. Product Quantization for Nearest Neighbor Search (2011) — 3,514 citations
  21. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016) — 3,491 citations
  22. Locality-sensitive hashing scheme based on p-stable distributions (2004) — 3,463 citations
  23. Object retrieval with large vocabularies and fast spatial matching (2007) — 3,312 citations
  24. Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration (2009) — 3,299 citations
  25. Learning to rank using gradient descent (2005) — 3,228 citations
  26. REALM: Retrieval-Augmented Language Model Pre-Training (2020, International Conference on Machine Learning) — 3,207 citations
  27. Similarity estimation techniques from rounding algorithms (2002) — 2,790 citations
  28. Unsupervised Learning by Probabilistic Latent Semantic Analysis (2004) — 2,727 citations
  29. Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions (2006) — 2,626 citations
  30. Using TF-IDF to Determine Word Relevance in Document Queries (2003) — 2,614 citations
  31. Open Information Extraction from the Web (2007) — 2,586 citations
  32. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016) — 2,486 citations
  33. Learning to rank: from pairwise approach to listwise approach (2007) — 2,421 citations
  34. Content-Based Image Retrieval at the End of the Early Years (2000) — 2,409 citations
  35. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT (2020) — 2,316 citations
  36. Learning deep structured semantic models for web search using clickthrough data (2013) — 2,275 citations
  37. Introduction to Information Retrieval (2008) — 2,258 citations
  38. Reading Wikipedia to Answer Open-Domain Questions (2017) — 2,232 citations
  39. Topic-sensitive PageRank (2002) — 2,160 citations
  40. Predict then Propagate: Graph Neural Networks meet Personalized PageRank (2018) — 2,108 citations
  41. Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search (2008) — 2,098 citations
  42. Rank aggregation methods for the Web (2001) — 2,068 citations
  43. Information Retrieval (2014) — 1,922 citations
  44. Placing search in context: the concept revisited (2002) — 1,875 citations
  45. Relevance-Based Language Models (2001) — 1,857 citations
  46. UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches (2014) — 1,846 citations
  47. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models (2021) — 1,831 citations
  48. Improving language models by retrieving from trillions of tokens (2021) — 1,785 citations
  49. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval (2020) — 1,631 citations
  50. Unsupervised Dense Information Retrieval with Contrastive Learning (2021) — 1,593 citations

Most active researchers

By papers in this topic: a volume measure, not trust.