An Introduction to Neural Information Retrieval
Abstract
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ supervised machine learning (ML) techniques—including neural networks—over hand-crafted IR features. By contrast, more recently proposed neural models learn representations of language from raw text that can bridge the gap between query and document vocabulary. Unlike classical learning to rank models and non-neural approaches to IR, these new ML techniques are data-hungry, requiring large scale training data before they can be deployed. This tutorial introduces basic concepts and intuitions behind neural IR models, and places them in the context of classical non-neural approaches to IR. We begin by introducing fundamental concepts of retrieval and different neural and non-neural approaches to unsupervised learning of vector representations of text. We then review IR methods that employ these pre-trained neural vector representations without learning the IR task end-to-end. We introduce the Learning to Rank (LTR) framework next, discussing standard loss functions for ranking. We follow that with an overview of deep neural networks (DNNs), including standard architectures and implementations. Finally, we review supervised neural learning to rank models, including recent DNN architectures trained end-to-end for ranking tasks. We conclude with a discussion on potential future directions for neural IR.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
As data and model capacity grew, learned systems increasingly absorbed factors that IR theories had enumerated explicitly, which accelerated progress but provided less conceptual scaffolding.
“As data and model capacity grew, learned systems increasingly absorbed factors that these theories had enumerated explicitly [40], which accelerated progress but provided less conceptual scaffolding.”
From Agentic Memory Management Is the Next Frontier of Information Retrieval (2026) · cites this paper as [40]
Cites
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1× · see citing works
“These breakthroughs were largely fuelled by recent advances in neural network models, usually with multiple hidden layers, known as deep architectures (Krizhevsky et al., 2012; LeCun et al., 2015; Hinton et al., 2012; Bahdanau et al., 2014; Deng, Yu, et al., 2014) combined with the availability of large datasets (Wiss…”
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · see citing works
Harris, Z. S. (1954) · <i>WORD</i> · doi:10.1080/00437956.1954.11659520 · Cited by 4,807 · see citing works
Singular value decomposition and least squares solutions
Golub, G. H., & Reinsch, C. (1970) · Numerische Mathematik · doi:10.1007/bf02163027 · Cited by 2,929 · cited 1× · see citing works
“, 1990] involves performing singular value decomposition (SVD) [Golub and Reinsch, 1970] on a term-document (or term-passage) matrix X to obtain its low-rank approximation [Markovsky, 2011].”
Accurately interpreting clickthrough data as implicit feedback
Joachims, T., Granka, L., Pan, B., Hembrooke, H., & Gay, G. (2005) · Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1076034.1076063 · Cited by 1,408 · see citing works
Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
Hahnloser, R. H. R., Sarpeshkar, R., Mahowald, M. A., Douglas, R. J., & Seung, H. S. (2000) · Nature · doi:10.1038/35016072 · Cited by 1,293 · see citing works
Plackett, R. L. (1975) · Applied Statistics · doi:10.2307/2346567 · Cited by 731 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.139 · Cited by 2,824 · see citing works
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
Khattab, O., & Zaharia, M. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401075 · Cited by 1,301 · see citing works
Sparse, Dense, and Attentional Representations for Text Retrieval
Luan, Y., Eisenstein, J., Toutanova, K., & Collins, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00369 · Cited by 363 · see citing works
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · arXiv · doi:10.48550/arxiv.2002.08155 · Cited by 243 · see citing works
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Xiong, L., Xiong, C., Li, Y., Tang, K.-F., Liu, J., Bennett, P., Ahmed, J., & Overwijk, A. (2020) · arXiv · doi:10.48550/arxiv.2007.00808 · Cited by 204 · see citing works
Rethinking search: making domain experts out of dilettantes
Metzler, D., Tay, Y., Bahri, D., & Najork, M. (2021) · ACM SIGIR Forum · doi:10.1145/3476415.3476428 · Cited by 112 · see citing works
Fast and Memory-Efficient Neural Code Completion
Svyatkovskiy, A., Lee, S., Hadjitofi, A., Riechert, M., Franco, J. V., & Allamanis, M. (2021) · 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr52588.2021.00045 · Cited by 95 · see citing works
Large-scale Training of Foundation Models for Wearable Biosignals
Abbaspourazad, S., Elachqar, O., Miller, A. C., Emrani, S., Nallasamy, U., & Shapiro, I. (2023) · arXiv · doi:10.48550/arxiv.2312.05409 · Cited by 28 · see citing works
Kazi, S., Khoja, S., & Daud, A. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100756 · Cited by 9 · see citing works
- Authors
- Mitra, B., & Craswell, N.
- Affiliations
- Microsoft (Canada) (CA)
- Microsoft (United States) (US)
- Venue
- Foundations and Trends® in Information Retrieval
- Publisher
- Emerald
- Published
- 2018-12-23
- Volume
- 13
- Issue
- 1
- Pages
- 1-126
- ISSN
- 1554-0669 (ISSN-L)
- 1554-0677
- OpenAlex
- W2725049817
- Cited by
- 317
- References
- 7
- Citations by year
- 2026: 28 · 2025: 29 · 2024: 23 · 2023: 35 · 2022: 33 · 2021: 67 · 2020: 53 · 2019: 37 · 2018: 8 · 2017: 3 · 2016: 1
- FWCI
- 64.04
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Foundations and Trends® in Information Retrieval (publishedVersion)
- CERN Document Server (European Organization for Nuclear Research) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- neural information retrieval, query processing, web search, scalable search, artificial neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
