Information retrieval#Model types

An information retrieval process begins when a user enters a query into the system. Queries are formal statements of information needs, for example search strings in web search engines. In information retrieval, a query does not uniquely identify a single object in the collection. Instead, several objects may match the query, perhaps with different degrees of relevance.

An object is an entity that is represented by information in a content collection or database. User queries are matched against the database information. However, as opposed to classical SQL queries of a database, in information retrieval the results returned may or may not match the query, so results are typically ranked. This ranking of results is a key difference of information retrieval searching compared to database searching.Jansen, B. J. and Rieh, S. (2010) [https://faculty.ist.psu.edu/jjansen/academic/jansen_theoretical_constructs.pdf The Seventeen Theoretical Constructs of Information Searching and Information Retrieval] {{Webarchive|url=https://web.archive.org/web/20160304195424/https://faculty.ist.psu.edu/jjansen/academic/jansen_theoretical_constructs.pdf |date=2016-03-04 }}. Journal of the American Society for Information Sciences and Technology. 61(8), 1517–1534.

Depending on the application the data objects may be, for example, text documents, images,{{cite journal |first=Abby A. |last=Goodrum |title=Image Information Retrieval: An Overview of Current Research |journal=Informing Science |volume=3 |number=2 |year=2000 }} audio,{{cite journal |first=Jonathan |last=Foote |title=An overview of audio information retrieval |journal=Multimedia Systems |volume=7 |pages=2–10 |year=1999 |doi=10.1007/s005300050106 |citeseerx=10.1.1.39.6339 |s2cid=2000641 }} mind maps{{cite conference |first1=Jöran |last1=Beel |first2=Bela |last2=Gipp |first3=Jan-Olaf |last3=Stiller |title=Information Retrieval On Mind Maps - What Could It Be Good For? |url=http://www.sciplore.org/publications_en.php |conference=Proceedings of the 5th International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom'09) |year=2009 |publisher=IEEE |place=Washington, DC |access-date=2012-03-13 |archive-url=https://web.archive.org/web/20110513214422/http://www.sciplore.org/publications_en.php |archive-date=2011-05-13 |url-status=dead }} or videos. Often the documents themselves are not kept or stored directly in the IR system, but are instead represented in the system by document surrogates or metadata.

Most IR systems compute a numeric score on how well each object in the database matches the query, and rank the objects according to this value. The top ranking objects are then shown to the user. The process may then be iterated if the user wishes to refine the query.{{cite book |last1=Frakes |first1=William B.|last2=Baeza-Yates|first2=Ricardo |title=Information Retrieval Data Structures & Algorithms |publisher=Prentice-Hall, Inc. |year=1992 |isbn=978-0-13-463837-9 |url=https://www.scribd.com/doc/13742235/Information-Retrieval-Data-Structures-Algorithms-William-B-Frakes |url-status=dead |archive-url=https://web.archive.org/web/20130928060217/http://www.scribd.com/doc/13742235/Information-Retrieval-Data-Structures-Algorithms-William-B-Frakes |archive-date=2013-09-28 }}

{{Rquote|right|there is ... a machine called the Univac ... whereby letters and figures are coded as a pattern of magnetic spots on a long steel tape. By this means the text of a document, preceded by its subject code symbol, can be recorded ... the machine ... automatically selects and types out those references which have been coded in any desired way at a rate of 120 words a minute| J. E. Holmstrom, 1948}}

The idea of using computers to search for relevant pieces of information was popularized in the article As We May Think by Vannevar Bush in 1945.{{cite journal |last=Singhal |first=Amit |title=Modern Information Retrieval: A Brief Overview |journal=Bulletin of the IEEE Computer Society Technical Committee on Data Engineering|volume=24 |issue=4 |pages=35–43 |year =2001 |url=http://singhal.info/ieee2001.pdf }} It would appear that Bush was inspired by patents for a 'statistical machine' – filed by Emanuel Goldberg in the 1920s and 1930s – that searched for documents stored on film.{{cite journal |author=Mark Sanderson & W. Bruce Croft |title=The History of Information Retrieval Research |journal=Proceedings of the IEEE |volume=100 |pages=1444–1451 |year =2012 |doi=10.1109/jproc.2012.2189916|doi-access=free }} The first description of a computer searching for information was described by Holmstrom in 1948,{{cite journal |author=JE Holmstrom |title='Section III. Opening Plenary Session |journal=The Royal Society Scientific Information Conference, 21 June-2 July 1948: Report and Papers Submitted |pages=85|year =1948|url=https://books.google.com/books?id=M34lAAAAMAAJ&q=univac}} detailing an early mention of the Univac computer. Automated information retrieval systems were introduced in the 1950s: one even featured in the 1957 romantic comedy Desk Set. In the 1960s, the first large information retrieval research group was formed by Gerard Salton at Cornell. By the 1970s several different retrieval techniques had been shown to perform well on small text corpora such as the Cranfield collection (several thousand documents). Large-scale retrieval systems, such as the Lockheed Dialog system, came into use early in the 1970s.

In 1992, the US Department of Defense along with the National Institute of Standards and Technology (NIST), cosponsored the Text Retrieval Conference (TREC) as part of the TIPSTER text program. The aim of this was to look into the information retrieval community by supplying the infrastructure that was needed for evaluation of text retrieval methodologies on a very large text collection. This catalyzed research on methods that scale to huge corpora. The introduction of web search engines has boosted the need for very large scale retrieval systems even further.

By the late 1990s, the rise of the World Wide Web fundamentally transformed information retrieval. While early search engines such as AltaVista (1995) and Yahoo! (1994) offered keyword-based retrieval, they were limited in scale and ranking refinement. The breakthrough came in 1998 with the founding of Google, which introduced the PageRank algorithm,{{Cite web |title=The Anatomy of a Search Engine |url=http://infolab.stanford.edu/~backrub/google.html |access-date=2025-04-09 |website=infolab.stanford.edu}} using the web’s hyperlink structure to assess page importance and improve relevance ranking.

During the 2000s, web search systems evolved rapidly with the integration of machine learning techniques. These systems began to incorporate user behavior data (e.g., click-through logs), query reformulation, and content-based signals to improve search accuracy and personalization. In 2009, Microsoft launched Bing, introducing features that would later incorporate semantic web technologies through the development of its Satori knowledge base. Academic analysis{{Cite journal |last1=Uyar |first1=Ahmet |last2=Aliyu |first2=Farouk Musa |date=2015-01-01 |title=Evaluating search features of Google Knowledge Graph and Bing Satori: Entity types, list searches and query interfaces |url=https://www.emerald.com/insight/content/doi/10.1108/oir-10-2014-0257/full/html |journal=Online Information Review |volume=39 |issue=2 |pages=197–213 |doi=10.1108/OIR-10-2014-0257 |issn=1468-4527}} have highlighted Bing’s semantic capabilities, including structured data use and entity recognition, as part of a broader industry shift toward improving search relevance and understanding user intent through natural language processing.

A major leap occurred in 2018, when Google deployed BERT (Bidirectional Encoder Representations from Transformers) to better understand the contextual meaning of queries and documents. This marked one of the first times deep neural language models were used at scale in real-world retrieval systems.{{cite arXiv | eprint=1810.04805 | last1=Devlin | first1=Jacob | last2=Chang | first2=Ming-Wei | last3=Lee | first3=Kenton | last4=Toutanova | first4=Kristina | title=BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | date=2018 | class=cs.CL }} BERT’s bidirectional training enabled a more refined comprehension of word relationships in context, improving the handling of natural language queries. Because of its success, transformer-based models gained traction in academic research and commercial search applications.{{Cite journal |last1=Gardazi |first1=Nadia Mushtaq |last2=Daud |first2=Ali |last3=Malik |first3=Muhammad Kamran |last4=Bukhari |first4=Amal |last5=Alsahfi |first5=Tariq |last6=Alshemaimri |first6=Bader |date=2025-03-15 |title=BERT applications in natural language processing: a review |url=https://link.springer.com/article/10.1007/s10462-025-11162-5 |journal=Artificial Intelligence Review |language=en |volume=58 |issue=6 |pages=166 |doi=10.1007/s10462-025-11162-5 |issn=1573-7462|doi-access=free }}

Simultaneously, the research community began exploring neural ranking models that outperformed traditional lexical-based methods. Long-standing benchmarks such as the Text REtrieval Conference (TREC), initiated in 1992, and more recent evaluation frameworks Microsoft MARCO(MAchine Reading COmprehension) (2019){{cite arXiv | eprint=1611.09268 | last1=Bajaj | first1=Payal | last2=Campos | first2=Daniel | last3=Craswell | first3=Nick | last4=Deng | first4=Li | last5=Gao | first5=Jianfeng | last6=Liu | first6=Xiaodong | last7=Majumder | first7=Rangan | last8=McNamara | first8=Andrew | last9=Mitra | first9=Bhaskar | last10=Nguyen | first10=Tri | last11=Rosenberg | first11=Mir | last12=Song | first12=Xia | last13=Stoica | first13=Alina | last14=Tiwary | first14=Saurabh | last15=Wang | first15=Tong | title=MS MARCO: A Human Generated MAchine Reading COmprehension Dataset | date=2016 | class=cs.CL }} became central to training and evaluating retrieval systems across multiple tasks and domains. MS MARCO has also been adopted in the TREC Deep Learning Tracks, where it serves as a core dataset for evaluating advances in neural ranking models within a standardized benchmarking environment.{{Cite journal |last1=Craswell |first1=Nick |last2=Mitra |first2=Bhaskar |last3=Yilmaz |first3=Emine |last4=Rahmani |first4=Hossein A. |last5=Campos |first5=Daniel |last6=Lin |first6=Jimmy |last7=Voorhees |first7=Ellen M. |last8=Soboroff |first8=Ian |date=2024-02-28 |title=Overview of the TREC 2023 Deep Learning Track |url=https://www.microsoft.com/en-us/research/publication/overview-of-the-trec-2023-deep-learning-track/ |language=en-US}}

As deep learning became integral to information retrieval systems, researchers began to categorize neural approaches into three broad classes: sparse, dense, and hybrid models. Sparse models, including traditional term-based methods and learned variants like SPLADE, rely on interpretable representations and inverted indexes to enable efficient exact term matching with added semantic signals.{{arxiv|2107.09226 }} Dense models, such as dual-encoder architectures like ColBERT, use continuous vector embeddings to support semantic similarity beyond keyword overlap.{{Cite book |last1=Khattab |first1=Omar |last2=Zaharia |first2=Matei |chapter=ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT |date=2020-07-25 |title=Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval |chapter-url=https://dl.acm.org/doi/10.1145/3397271.3401075 |series=SIGIR '20 |location=New York, NY, USA |publisher=Association for Computing Machinery |pages=39–48 |doi=10.1145/3397271.3401075 |isbn=978-1-4503-8016-4}} Hybrid models aim to combine the advantages of both, balancing the lexical (token) precision of sparse methods with the semantic depth of dense models. This way of categorizing models balances scalability, relevance, and efficiency in retrieval systems.{{cite arXiv | eprint=2010.06467 | last1=Lin | first1=Jimmy | last2=Nogueira | first2=Rodrigo | last3=Yates | first3=Andrew | title=Pretrained Transformers for Text Ranking: BERT and Beyond | date=2020 | class=cs.IR }}

As IR systems increasingly rely on deep learning, concerns around bias, fairness, and explainability have also come to the picture. Research is now focused not just on relevance and efficiency, but on transparency, accountability, and user trust in retrieval algorithms.

Areas where information retrieval techniques are employed include (the entries are in alphabetical order within each category):

• Digital libraries
• Information filtering
• Recommender systems
• Media search
• Blog search
• Image retrieval
• 3D retrieval
• Music retrieval
• News search
• Speech retrieval
• Video retrieval
• Search engines
• Site search
• Desktop search
• Enterprise search
• Federated search
• Mobile search
• Social search
• Web search

• Expert search finding
• Genomic information retrieval
• Geographic information retrieval
• Information retrieval for chemical structures
• Information retrieval in software engineering
• Legal information retrieval
• Vertical search

Methods/Techniques in which information retrieval techniques are employed include:

• Adversarial information retrieval
• Automatic summarization
• Multi-document summarization
• Compound term processing
• Cross-lingual retrieval
• Document classification
• Spam filtering
• Question answering

File:Information-Retrieval-Models.png, original source [http://www.logos-verlag.de/cgi-bin/engbuchmid?isbn=0514&lng=eng&id= Dominik Kuropka])]]

In order to effectively retrieve relevant documents by IR strategies, the documents are typically transformed into a suitable representation. Each retrieval strategy incorporates a specific model for its document representation purposes. The picture on the right illustrates the relationship of some common models. In the picture, the models are categorized according to two dimensions: the mathematical basis and the properties of the model.

• Set-theoretic models represent documents as sets of words or phrases. Similarities are usually derived from set-theoretic operations on those sets. Common models are:
• Standard Boolean model
• Extended Boolean model
• Fuzzy retrieval
• Algebraic models represent documents and queries usually as vectors, matrices, or tuples. The similarity of the query vector and document vector is represented as a scalar value.
• Vector space model
• Generalized vector space model
• (Enhanced) Topic-based Vector Space Model
• Extended Boolean model
• Latent semantic indexing a.k.a. latent semantic analysis
• Probabilistic models treat the process of document retrieval as a probabilistic inference. Similarities are computed as probabilities that a document is relevant for a given query. Probabilistic theorems like Bayes' theorem are often used in these models.
• Binary Independence Model
• Probabilistic relevance model on which is based the okapi (BM25) relevance function
• Uncertain inference
• Language models
• Divergence-from-randomness model
• Latent Dirichlet allocation
• Feature-based retrieval models view documents as vectors of values of feature functions (or just features) and seek the best way to combine these features into a single relevance score, typically by learning to rank methods. Feature functions are arbitrary functions of document and query, and as such can easily incorporate almost any other retrieval model as just another feature.

• Models without term-interdependencies treat different terms/words as independent. This fact is usually represented in vector space models by the orthogonality assumption of term vectors or in probabilistic models by an independency assumption for term variables.
• Models with immanent term interdependencies allow a representation of interdependencies between terms. However the degree of the interdependency between two terms is defined by the model itself. It is usually directly or indirectly derived (e.g. by dimensional reduction) from the co-occurrence of those terms in the whole set of documents.
• Models with transcendent term interdependencies allow a representation of interdependencies between terms, but they do not allege how the interdependency between two terms is defined. They rely on an external source for the degree of interdependency between two terms. (For example, a human or sophisticated algorithms.)

In addition to the theoretical distinctions, modern information retrieval models are also categorized on how queries and documents are represented and compared, using a practical classification distinguishing between sparse, dense and hybrid models.{{cite arXiv | eprint=2107.09226 | last1=Kim | first1=Dohyun | last2=Zhao | first2=Lina | last3=Chung | first3=Eric | last4=Park | first4=Eun-Jae | title=Pressure-robust staggered DG methods for the Navier-Stokes equations on general meshes | date=2021 | class=math.NA }}

• Sparse models utilize interpretable, term-based representations and typically rely on inverted index structures. Classical methods such as TF-IDF and BM25 fall under this category, along with more recent learned sparse models that integrate neural architectures while retaining sparsity.{{cite arXiv | eprint=2104.08663 | last1=Thakur | first1=Nandan | last2=Reimers | first2=Nils | last3=Rücklé | first3=Andreas | last4=Srivastava | first4=Abhishek | last5=Gurevych | first5=Iryna | title=BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models | date=2021 | class=cs.IR }}
• Dense models represent queries and documents as continuous vectors using deep learning models, typically transformer-based encoders. These models enable semantic similarity matching beyond exact term overlap and are used in tasks involving semantic search and question answering.{{Cite journal |last1=Lau |first1=Jey Han |last2=Armendariz |first2=Carlos |last3=Lappin |first3=Shalom |last4=Purver |first4=Matthew |last5=Shu |first5=Chang |date=2020 |editor-last=Johnson |editor-first=Mark |editor2-last=Roark |editor2-first=Brian |editor3-last=Nenkova |editor3-first=Ani |title=How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context |url=https://aclanthology.org/2020.tacl-1.20/ |journal=Transactions of the Association for Computational Linguistics |volume=8 |pages=296–310 |doi=10.1162/tacl_a_00315}}
• Hybrid models aim to combine the strengths of both approaches, integrating lexical (tokens) and semantic signals through score fusion, late interaction, or multi-stage ranking pipelines.{{cite arXiv | eprint=2109.10739 | last1=Arabzadeh | first1=Negar | last2=Yan | first2=Xinyi | last3=Clarke | first3=Charles L. A. | title=Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection | date=2021 | class=cs.IR }}

This classification has become increasingly common in both academic and the real world applications and is getting widely adopted and used in evaluation benchmarks for Information Retrieval models.{{cite arXiv | eprint=2010.06467 | last1=Lin | first1=Jimmy | last2=Nogueira | first2=Rodrigo | last3=Yates | first3=Andrew | title=Pretrained Transformers for Text Ranking: BERT and Beyond | date=2020 | class=cs.IR }}

{{main|Evaluation measures (information retrieval)}}

The evaluation of an information retrieval system' is the process of assessing how well a system meets the information needs of its users. In general, measurement considers a collection of documents to be searched and a search query. Traditional evaluation metrics, designed for Boolean retrieval{{huh|date=June 2018}} or top-k retrieval, include precision and recall. All measures assume a ground truth notion of relevance: every document is known to be either relevant or non-relevant to a particular query. In practice, queries may be ill-posed and there may be different shades of relevance.

• Lemur
• Lucene
• Solr
• Elasticsearch
• Manatee
• Manticore search
• Sphinx
• Terrier Search Engine
• Xapian

• Before the 1900s
• : 1801: Joseph Marie Jacquard invents the Jacquard loom, the first machine to use punched cards to control a sequence of operations.
• : 1880s: Herman Hollerith invents an electro-mechanical data tabulator using punch cards as a machine readable medium.
• : 1890 Hollerith cards, keypunches and tabulators used to process the 1890 US census data.
• 1920s–1930s
• : Emanuel Goldberg submits patents for his "Statistical Machine", a document search engine that used photoelectric cells and pattern recognition to search the metadata on rolls of microfilmed documents.
• 1940s–1950s
• : late 1940s: The US military confronted problems of indexing and retrieval of wartime scientific research documents captured from Germans.
• :: 1945: Vannevar Bush's As We May Think appeared in Atlantic Monthly.
• :: 1947: Hans Peter Luhn (research engineer at IBM since 1941) began work on a mechanized punch card-based system for searching chemical compounds.
• : 1950s: Growing concern in the US for a "science gap" with the USSR motivated, encouraged funding and provided a backdrop for mechanized literature searching systems (Allen Kent et al.) and the invention of the citation index by Eugene Garfield.
• : 1950: The term "information retrieval" was coined by Calvin Mooers.Mooers, Calvin N.; [https://babel.hathitrust.org/cgi/pt?id=mdp.39015034570591;view=1up;seq=3 The Theory of Digital Handling of Non-numerical Information and its Implications to Machine Economics] (Zator Technical Bulletin No. 48), cited in {{cite journal|last1=Fairthorne|first1=R. A.|title=Automatic Retrieval of Recorded Information|journal=The Computer Journal|date=1958|volume=1|issue=1|page=37|doi=10.1093/comjnl/1.1.36|doi-access=free}}
• : 1951: Philip Bagley conducted the earliest experiment in computerized document retrieval in a master thesis at MIT.{{cite book |last1=Doyle |first1=Lauren |last2=Becker |first2=Joseph |title=Information Retrieval and Processing |publisher=Melville |year=1975 |pages=410 pp |isbn=978-0-471-22151-7 }}
• : 1955: Allen Kent joined Case Western Reserve University, and eventually became associate director of the Center for Documentation and Communications Research. That same year, Kent and colleagues published a paper in American Documentation describing the precision and recall measures as well as detailing a proposed "framework" for evaluating an IR system which included statistical sampling methods for determining the number of relevant documents not retrieved.{{cite journal |title=Machine literature searching X. Machine language; factors underlying its design and development |journal=American Documentation|volume=6|issue=4|pages=242–254|doi=10.1002/asi.5090060411|year=1955|last1=Perry|first1=James W.|last2=Kent|first2=Allen|last3=Berry|first3=Madeline M.}}
• : 1958: International Conference on Scientific Information Washington DC included consideration of IR systems as a solution to problems identified. See: Proceedings of the International Conference on Scientific Information, 1958 (National Academy of Sciences, Washington, DC, 1959)
• : 1959: Hans Peter Luhn published "Auto-encoding of documents for information retrieval".
• 1960s:
• : early 1960s: Gerard Salton began work on IR at Harvard, later moved to Cornell.
• : 1960: Melvin Earl Maron and John Lary Kuhns{{cite journal |title=An Historical Note on the Origins of Probabilistic Indexing |last=Maron | first=Melvin E. |journal=Information Processing and Management |volume=44 |year=2008 |pages=971–972 |url=http://yunus.hacettepe.edu.tr/~tonta/courses/spring2008/bby703/maron-on-probabilistic%20indexing-2008.pdf |doi=10.1016/j.ipm.2007.02.012 |issue=2 }} published "On relevance, probabilistic indexing, and information retrieval" in the Journal of the ACM 7(3):216–244, July 1960.
• : 1962:
• :* Cyril W. Cleverdon published early findings of the Cranfield studies, developing a model for IR system evaluation. See: Cyril W. Cleverdon, "Report on the Testing and Analysis of an Investigation into the Comparative Efficiency of Indexing Systems". Cranfield Collection of Aeronautics, Cranfield, England, 1962.
• :* Kent published Information Analysis and Retrieval.
• : 1963:
• :* Weinberg report "Science, Government and Information" gave a full articulation of the idea of a "crisis of scientific information". The report was named after Dr. Alvin Weinberg.
• :* Joseph Becker and Robert M. Hayes published text on information retrieval. Becker, Joseph; Hayes, Robert Mayo. Information storage and retrieval: tools, elements, theories. New York, Wiley (1963).
• : 1964:
• :* Karen Spärck Jones finished her thesis at Cambridge, Synonymy and Semantic Classification, and continued work on computational linguistics as it applies to IR.
• :* The National Bureau of Standards sponsored a symposium titled "Statistical Association Methods for Mechanized Documentation". Several highly significant papers, including G. Salton's first published reference (we believe) to the SMART system.
• :mid-1960s:
• ::* National Library of Medicine developed MEDLARS Medical Literature Analysis and Retrieval System, the first major machine-readable database and batch-retrieval system.
• ::* Project Intrex at MIT.
• :: 1965: J. C. R. Licklider published Libraries of the Future.
• :: 1966: Don Swanson was involved in studies at University of Chicago on Requirements for Future Catalogs.
• : late 1960s: F. Wilfrid Lancaster completed evaluation studies of the MEDLARS system and published the first edition of his text on information retrieval.
• :: 1968:
• :* Gerard Salton published Automatic Information Organization and Retrieval.
• :* John W. Sammon, Jr.'s RADC Tech report "Some Mathematics of Information Storage and Retrieval..." outlined the vector model.
• :: 1969: Sammon's "[http://studentnet.cs.manchester.ac.uk/pgt/COMP61021/reference/Sammon.pdf A nonlinear mapping for data structure analysis] {{Webarchive|url=https://web.archive.org/web/20170808172524/http://studentnet.cs.manchester.ac.uk/pgt/COMP61021/reference/Sammon.pdf |date=2017-08-08 }}" (IEEE Transactions on Computers) was the first proposal for visualization interface to an IR system.
• 1970s
• : early 1970s:
• ::* First online systems—NLM's AIM-TWX, MEDLINE; Lockheed's Dialog; SDC's ORBIT.
• ::* Theodor Nelson promoting concept of hypertext, published Computer Lib/Dream Machines.
• : 1971: Nicholas Jardine and Cornelis J. van Rijsbergen published "The use of hierarchic clustering in information retrieval", which articulated the "cluster hypothesis".{{cite journal|author=N. Jardine, C.J. van Rijsbergen|title=The use of hierarchic clustering in information retrieval|journal=Information Storage and Retrieval|volume=7|issue=5|pages=217–240|date=December 1971|doi=10.1016/0020-0271(71)90051-9}}
• : 1975: Three highly influential publications by Salton fully articulated his vector processing framework and term discrimination model:
• ::* A Theory of Indexing (Society for Industrial and Applied Mathematics)
• ::* A Theory of Term Importance in Automatic Text Analysis (JASIS v. 26)
• ::* A Vector Space Model for Automatic Indexing (CACM 18:11)
• : 1978: The First ACM SIGIR conference.
• : 1979: C. J. van Rijsbergen published Information Retrieval (Butterworths). Heavy emphasis on probabilistic models.
• : 1979: Tamas Doszkocs implemented the CITE natural language user interface for MEDLINE at the National Library of Medicine. The CITE system supported free form query input, ranked output and relevance feedback.Doszkocs, T.E. & Rapp, B.A. (1979). "Searching MEDLINE in English: a Prototype User Interface with Natural Language Query, Ranked Output, and relevance feedback," In: Proceedings of the ASIS Annual Meeting, 16: 131–139.
• 1980s
• : 1980: First international ACM SIGIR conference, joint with British Computer Society IR group in Cambridge.
• : 1982: Nicholas J. Belkin, Robert N. Oddy, and Helen M. Brooks proposed the ASK (Anomalous State of Knowledge) viewpoint for information retrieval. This was an important concept, though their automated analysis tool proved ultimately disappointing.
• : 1983: Salton (and Michael J. McGill) published Introduction to Modern Information Retrieval (McGraw-Hill), with heavy emphasis on vector models.
• : 1985: David Blair and Bill Maron publish: An Evaluation of Retrieval Effectiveness for a Full-Text Document-Retrieval System
• : mid-1980s: Efforts to develop end-user versions of commercial IR systems.
• :: 1985–1993: Key papers on and experimental systems for visualization interfaces.
• :: Work by Donald B. Crouch, Robert R. Korfhage, Matthew Chalmers, Anselm Spoerri and others.
• : 1989: First World Wide Web proposals by Tim Berners-Lee at CERN.
• 1990s
• : 1992: First TREC conference.
• : 1997: Publication of Korfhage's Information Storage and Retrieval{{cite book |last=Korfhage |first=Robert R. |title=Information Storage and Retrieval |publisher=Wiley |year=1997 |pages=[https://archive.org/details/informationstora00korf/page/368 368 pp] |isbn=978-0-471-14338-3 |url=https://archive.org/details/informationstora00korf/page/368 |url-access=registration }} with emphasis on visualization and multi-reference point systems.
• : 1998: Google is founded by Larry Page and Sergey Brin. It introduces the PageRank algorithm, which evaluates the importance of web pages based on hyperlink structure.{{Cite web |title=The Anatomy of a Search Engine |url=http://infolab.stanford.edu/~backrub/google.html |access-date=2025-04-09 |website=infolab.stanford.edu}}
• : 1999: Publication of Ricardo Baeza-Yates and Berthier Ribeiro-Neto's Modern Information Retrieval by Addison Wesley, the first book that attempts to cover all IR.
• 2000s
• : 2001: Wikipedia launches as a free, collaborative online encyclopedia. It quickly becomes a major resource for information retrieval, particularly for natural language processing and semantic search benchmarks.{{Citation |title=History of Wikipedia |date=2025-02-21 |work=Wikipedia |url=https://en.wikipedia.org/wiki/History_of_Wikipedia |access-date=2025-04-09 |language=en}}
• : 2009: Microsoft launches Bing, introducing features such as related searches, semantic suggestions, and later incorporating deep learning techniques into its ranking algorithms.{{Cite journal |last1=Uyar |first1=Ahmet |last2=Aliyu |first2=Farouk Musa |date=2015-01-01 |title=Evaluating search features of Google Knowledge Graph and Bing Satori: Entity types, list searches and query interfaces |url=https://www.emerald.com/insight/content/doi/10.1108/oir-10-2014-0257/full/html |journal=Online Information Review |volume=39 |issue=2 |pages=197–213 |doi=10.1108/OIR-10-2014-0257 |issn=1468-4527}}
• 2010s
• : 2013: Google’s Hummingbird algorithm goes live, marking a shift from keyword matching toward understanding query intent and semantic context in search queries.{{Cite web |last=Sullivan |first=Danny |date=2013-09-26 |title=FAQ: All About The New Google "Hummingbird" Algorithm |url=https://searchengineland.com/google-hummingbird-172816 |access-date=2025-04-09 |website=Search Engine Land |language=en}}
• : 2018: Google AI researchers release BERT (Bidirectional Encoder Representations from Transformers), enabling deep bidirectional understanding of language and improving document ranking and query understanding in IR.{{cite arXiv | eprint=1810.04805 | last1=Devlin | first1=Jacob | last2=Chang | first2=Ming-Wei | last3=Lee | first3=Kenton | last4=Toutanova | first4=Kristina | title=BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | date=2018 | class=cs.CL }}
• : 2019: Microsoft introduces MS MARCO (Microsoft MAchine Reading COmprehension), a large-scale dataset designed for training and evaluating machine reading and passage ranking models.{{cite arXiv | eprint=1611.09268 | last1=Bajaj | first1=Payal | last2=Campos | first2=Daniel | last3=Craswell | first3=Nick | last4=Deng | first4=Li | last5=Gao | first5=Jianfeng | last6=Liu | first6=Xiaodong | last7=Majumder | first7=Rangan | last8=McNamara | first8=Andrew | last9=Mitra | first9=Bhaskar | last10=Nguyen | first10=Tri | last11=Rosenberg | first11=Mir | last12=Song | first12=Xia | last13=Stoica | first13=Alina | last14=Tiwary | first14=Saurabh | last15=Wang | first15=Tong | title=MS MARCO: A Human Generated MAchine Reading COmprehension Dataset | date=2016 | class=cs.CL }}
• 2020s
• : 2020: The ColBERT (Contextualized Late Interaction over BERT) model, designed for efficient passage retrieval using contextualized embeddings, was introduced at SIGIR 2020.{{cite arXiv | eprint=2004.12832 | last1=Khattab | first1=Omar | last2=Zaharia | first2=Matei | title=ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT | date=2020 | class=cs.IR }}{{Cite book |last1=Khattab |first1=Omar |last2=Zaharia |first2=Matei |chapter=ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT |date=2020-07-25 |title=Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval |chapter-url=https://dl.acm.org/doi/10.1145/3397271.3401075 |series=SIGIR '20 |location=New York, NY, USA |publisher=Association for Computing Machinery |pages=39–48 |doi=10.1145/3397271.3401075 |isbn=978-1-4503-8016-4}}
• : 2021: SPLADE is introduced at SIGIR 2021. It’s a sparse neural retrieval model that balances lexical and semantic features using masked language modeling and sparsity regularization.{{Cite book |last1=Jones |first1=Rosie |last2=Zamani |first2=Hamed |last3=Schedl |first3=Markus |last4=Chen |first4=Ching-Wei |last5=Reddy |first5=Sravana |last6=Clifton |first6=Ann |last7=Karlgren |first7=Jussi |last8=Hashemi |first8=Helia |last9=Pappu |first9=Aasish |last10=Nazari |first10=Zahra |last11=Yang |first11=Longqi |last12=Semerci |first12=Oguz |last13=Bouchard |first13=Hugues |last14=Carterette |first14=Ben |chapter=Current Challenges and Future Directions in Podcast Information Access |date=2021-07-11 |title=Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval |chapter-url=https://dl.acm.org/doi/10.1145/3404835.3462805 |series=SIGIR '21 |location=New York, NY, USA |publisher=Association for Computing Machinery |pages=1554–1565 |doi=10.1145/3404835.3462805 |arxiv=2106.09227 |isbn=978-1-4503-8037-9}}
• : 2022: The BEIR benchmark is released to evaluate zero-shot IR across 18 datasets covering diverse tasks. It standardizes comparisons between dense, sparse, and hybrid IR models.{{cite arXiv | eprint=2104.08663 | last1=Thakur | first1=Nandan | last2=Reimers | first2=Nils | last3=Rücklé | first3=Andreas | last4=Srivastava | first4=Abhishek | last5=Gurevych | first5=Iryna | title=BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models | date=2021 | class=cs.IR }}

• SIGIR: Special Interest Group on Information Retrieval
• ECIR: European Conference on Information Retrieval
• CIKM: Conference on Information and Knowledge Management
• WWW: International World Wide Web Conference

• Tony Kent Strix award
• Gerard Salton Award
• Karen Spärck Jones Award

{{div col}}

• {{annotated link|Adversarial information retrieval}}
• {{annotated link|Computer memory}}
• {{annotated link|Controlled vocabulary}}
• {{annotated link|Cross-language information retrieval}}
• {{annotated link|Data mining}}
• {{annotated link|Data retrieval}}
• {{annotated link|European Summer School in Information Retrieval}}
• {{annotated link|Human–computer information retrieval|abbreviation=HCIR}}
• {{annotated link|Information extraction}}
• {{annotated link|Information seeking}}
• {{section link|Information seeking|Compared to information retrieval}}
• {{annotated link|Collaborative information seeking}}
• {{annotated link|Social information seeking}}
• {{annotated link|Information Retrieval Facility}}
• {{annotated link|Knowledge visualization}}
• {{annotated link|Multimedia information retrieval}}
• {{annotated link|Personal information management}}
• {{annotated link|Pearl growing}}
• {{annotated link|Query understanding}}
• {{annotated link|Relevance (information retrieval)}}
• {{annotated link|Relevance feedback}}
• {{annotated link|Nearest centroid classifier|Rocchio classification}}
• {{annotated link|Search engine indexing}}
• {{annotated link|Special Interest Group on Information Retrieval}}
• {{annotated link|Subject indexing}}
• {{annotated link|Temporal information retrieval}}
• {{annotated link|tf–idf}}
• {{annotated link|XML retrieval}}
• {{annotated link|Web mining}}

{{div col end}}

{{reflist}}

• Ricardo Baeza-Yates, Berthier Ribeiro-Neto. [http://www.mir2ed.org/ Modern Information Retrieval: The Concepts and Technology behind Search (second edition)] {{Webarchive|url=https://web.archive.org/web/20170918235142/http://mir2ed.org/ |date=2017-09-18 }}. Addison-Wesley, UK, 2011.
• Stefan Büttcher, Charles L. A. Clarke, and Gordon V. Cormack. [http://www.ir.uwaterloo.ca/book/ Information Retrieval: Implementing and Evaluating Search Engines] {{Webarchive|url=https://web.archive.org/web/20201005195805/http://www.ir.uwaterloo.ca/book/ |date=2020-10-05 }}. MIT Press, Cambridge, Massachusetts, 2010.
• {{cite web | title=Information Retrieval System | website=Library & Information Science Network | date=24 April 2015 | url=http://www.lisbdnet.com/information-retrieval-syste/ | access-date=3 May 2020 | archive-date=11 May 2020 | archive-url=https://web.archive.org/web/20200511161049/http://www.lisbdnet.com/information-retrieval-syste | url-status=dead }}
• Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. [https://nlp.stanford.edu/IR-book/ Introduction to Information Retrieval]. Cambridge University Press, 2008.
• Yeo, ShinJoung. (2023) Behind the Search Box: Google and the Global Internet Industry (U of Illinois Press, 2023) {{ISBN|0252087127}} [https://www.jstor.org/stable/10.5406/jj.4116455 online]

{{wikiquote}}

{{Commonscat}}

• [https://sigir.org/ ACM SIGIR: Information Retrieval Special Interest Group]
• [https://www.bcs.org/membership-and-registrations/member-communities/information-retrieval-specialist-group BCS IRSG: British Computer Society – Information Retrieval Specialist Group]
• [https://trec.nist.gov/ Text Retrieval Conference (TREC)]
• [http://www.isical.ac.in/~fire Forum for Information Retrieval Evaluation (FIRE)]
• [https://www.dcs.gla.ac.uk/Keith/Preface.html Information Retrieval] (online book) by C. J. van Rijsbergen
• [http://ir.dcs.gla.ac.uk/wiki/ Information Retrieval Wiki] {{Webarchive|url=https://web.archive.org/web/20151124065507/http://ir.dcs.gla.ac.uk/wiki |date=2015-11-24 }}
• [http://ir-facility.org/ Information Retrieval Facility] {{Webarchive|url=https://web.archive.org/web/20080522151226/http://www.ir-facility.org/ |date=2008-05-22 }}
• [https://trec.nist.gov/pubs/trec15/appendices/CE.MEASURES06.pdf TREC report on information retrieval evaluation techniques]
• [https://innovation.ebayinc.com/tech/engineering/measuring-search-relevance/ How eBay measures search relevance]
• [http://retrieval.ceti.gr Information retrieval performance evaluation tool @ Athena Research Centre]

{{Authority control}}

{{DEFAULTSORT:Information Retrieval}}

Category:Natural language processing