{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:36:36Z","timestamp":1777307796382,"version":"3.51.4"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["2022XERWK9"],"award-info":[{"award-number":["2022XERWK9"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.inffus.2026.104291","type":"journal-article","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T16:14:51Z","timestamp":1773504891000},"page":"104291","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Semantic-aware data imputation in dynamic relational databases via pre-trained language models"],"prefix":"10.1016","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7280-4759","authenticated-orcid":false,"given":"Gianvincenzo","family":"Alfano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2966-3484","authenticated-orcid":false,"given":"Sergio","family":"Greco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3324-0580","authenticated-orcid":false,"given":"Lucio","family":"La Cava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6870-7509","authenticated-orcid":false,"given":"Tariq","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9031-0672","authenticated-orcid":false,"given":"Irina","family":"Trubitsyna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104291_sbref0001","series-title":"Foundations of Databases: The Logical Level","author":"Abiteboul","year":"1995"},{"key":"10.1016\/j.inffus.2026.104291_bib0002","series-title":"Handbook of Data Quality: Research and Practice","first-page":"163","article-title":"Data glitches: monsters in your data","author":"Dasu","year":"2013"},{"key":"10.1016\/j.inffus.2026.104291_bib0003","doi-asserted-by":"crossref","unstructured":"T. Dasu, J.M. Loh, D. Srivastava, Empirical glitch explanations572\u2013581. https:\/\/doi.org\/10.1145\/2623330.2623716.","DOI":"10.1145\/2623330.2623716"},{"issue":"4","key":"10.1016\/j.inffus.2026.104291_bib0004","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1177\/1094428114548590","article-title":"Missing data: five practical guidelines","volume":"17","author":"Newman","year":"2014","journal-title":"Organ. Res. Methods"},{"key":"10.1016\/j.inffus.2026.104291_bib0005","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.is.2019.03.010","article-title":"Approximation algorithms for querying incomplete databases","volume":"86","author":"Greco","year":"2019","journal-title":"Inf. Syst."},{"key":"10.1016\/j.inffus.2026.104291_bib0006","series-title":"Proceedings of the PODS Conference, 2023","first-page":"11","article-title":"SQL nulls and two-valued logic","author":"Libkin","year":"2023"},{"issue":"24","key":"10.1016\/j.inffus.2026.104291_bib0007","doi-asserted-by":"crossref","first-page":"3050","DOI":"10.1002\/elps.201500352","article-title":"Missing value imputation strategies for metabolomics data","volume":"36","author":"Armitage","year":"2015","journal-title":"Electrophoresis"},{"key":"10.1016\/j.inffus.2026.104291_bib0008","doi-asserted-by":"crossref","DOI":"10.3389\/fdata.2021.693674","article-title":"A benchmark for data imputation methods","volume":"4","author":"J\u00e4ger","year":"2021","journal-title":"Front. Big Data"},{"issue":"2","key":"10.1016\/j.inffus.2026.104291_bib0009","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1109\/TPAMI.2017.2688363","article-title":"Multi-target regression via robust low-rank learning","volume":"40","author":"Zhen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104291_bib0010","article-title":"Dynamic spatial-temporal imputation network with missing features for traffic data imputation","author":"Li","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.inffus.2026.104291_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.simpat.2025.103178","article-title":"Exploring the performance of real-time data imputation to enhance fault tolerance on the edge: a study on environmental data","volume":"144","author":"Gkoulis","year":"2025","journal-title":"Simul. Modell. Pract. Theory"},{"issue":"4","key":"10.1016\/j.inffus.2026.104291_bib0012","first-page":"29","article-title":"Imputation and classification of missing data using least square support vector machines\u2013a new approach in dementia diagnosis","volume":"1","author":"Sivapriya","year":"2012","journal-title":"Int. J. Adv. Res. Artif. Intell."},{"issue":"8","key":"10.1016\/j.inffus.2026.104291_bib0013","doi-asserted-by":"crossref","first-page":"2933","DOI":"10.1109\/TITS.2018.2869768","article-title":"Missing value imputation for traffic-related time series data based on a multi-view learning method","volume":"20","author":"Li","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"10","key":"10.1016\/j.inffus.2026.104291_bib0014","doi-asserted-by":"crossref","first-page":"2832","DOI":"10.3390\/s20102832","article-title":"A novel LSTM for multivariate time series with massive missingness","volume":"20","author":"Fouladgar","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.inffus.2026.104291_bib0015","series-title":"International Conference on Neural Information Processing","first-page":"258","article-title":"Iterative imputation of missing data using auto-encoder dynamics","author":"\u015amieja","year":"2020"},{"issue":"2","key":"10.1016\/j.inffus.2026.104291_bib0016","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3390\/computers9020037","article-title":"Complex data imputation by auto-encoders and convolutional neural networks\u2013a case study on genome gap-filling","volume":"9","author":"Cappelletti","year":"2020","journal-title":"Computers"},{"key":"10.1016\/j.inffus.2026.104291_bib0017","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2023.3306721","article-title":"Generative adversarial networks assist missing data imputation: a comprehensive survey & evaluation","author":"Shahbazian","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104291_bib0018","series-title":"Proceedings 27th International Conference on Extending Database Technology, EDBT, Paestum, Italy","article-title":"Relational data imputation with graph neural networks","author":"Cappuzzo","year":"2024"},{"key":"10.1016\/j.inffus.2026.104291_bib0019","series-title":"Proc. of IEEE International Conference on Data Engineering (ICDE)","first-page":"61","article-title":"Capturing semantics for imputation with pre-trained language models","author":"Mei","year":"2021"},{"key":"10.1016\/j.inffus.2026.104291_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102524","article-title":"Imputation of missing values in multi-view data","volume":"111","author":"Van Loon","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104291_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102292","article-title":"Hierarchical spatio-temporal graph convolutional neural networks for traffic data imputation","volume":"106","author":"Xu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104291_bib0022","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1016\/j.inffus.2021.07.001","article-title":"Advances in data preprocessing for biomedical data fusion: an overview of the methods, challenges, and prospects","volume":"76","author":"Wang","year":"2021","journal-title":"Inf. Fusion"},{"issue":"6","key":"10.1016\/j.inffus.2026.104291_bib0023","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1145\/362384.362685","article-title":"A relational model of data for large shared data banks","volume":"13","author":"Codd","year":"1970","journal-title":"Commun. ACM"},{"key":"10.1016\/j.inffus.2026.104291_bib0024","doi-asserted-by":"crossref","unstructured":"N. Reimers, I. Gurevych, Sentence-BERT: sentence embeddings using siamese BERT-networks (2019) 3973\u20133983. 10.18653\/v1\/D19-1410.","DOI":"10.18653\/v1\/D19-1410"},{"issue":"3","key":"10.1016\/j.inffus.2026.104291_bib0025","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","article-title":"Inference and missing data","volume":"63","author":"Rubin","year":"1976","journal-title":"Biometrika"},{"key":"10.1016\/j.inffus.2026.104291_bib0026","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/s10044-014-0376-8","article-title":"A hybrid clustering algorithm based on missing attribute interval estimation for incomplete data","volume":"18","author":"Zhang","year":"2015","journal-title":"Pattern Anal. Appl."},{"issue":"2","key":"10.1016\/j.inffus.2026.104291_bib0027","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s10115-015-0822-y","article-title":"Missing value imputation using a fuzzy clustering-based EM approach","volume":"46","author":"Rahman","year":"2016","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.inffus.2026.104291_bib0028","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.engappai.2019.03.003","article-title":"A novel purity-based k nearest neighbors imputation method and its application in financial distress prediction","volume":"81","author":"Cheng","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.inffus.2026.104291_bib0029","series-title":"Intelligent Systems and Applications: Proceedings of the 2019 Intelligent Systems Conference (IntelliSys) Volume 1","first-page":"486","article-title":"A hierarchical missing value imputation method by correlation-based K-nearest neighbors","author":"Liu","year":"2020"},{"key":"10.1016\/j.inffus.2026.104291_bib0030","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2020.06.005","article-title":"Missing data imputation with adversarially-trained graph convolutional networks","volume":"129","author":"Spinelli","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2026.104291_bib0031","first-page":"19075","article-title":"Handling missing data with graph representation learning","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104291_bib0032","doi-asserted-by":"crossref","DOI":"10.3389\/fdata.2021.693869","article-title":"TSI-GNN: extending graph neural networks to handle missing data in temporal settings","volume":"4","author":"Gordon","year":"2021","journal-title":"Front. Big Data"},{"key":"10.1016\/j.inffus.2026.104291_bib0033","series-title":"Advances in Knowledge Discovery and Data Mining","first-page":"260","article-title":"Mida: multiple imputation using denoising autoencoders","author":"Gondara","year":"2018"},{"key":"10.1016\/j.inffus.2026.104291_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107501","article-title":"Handling incomplete heterogeneous data using vaes","volume":"107","author":"Nazabal","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.inffus.2026.104291_bib0035","series-title":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","first-page":"454","article-title":"A survey of missing data imputation using generative adversarial networks","author":"Kim","year":"2020"},{"issue":"10","key":"10.1016\/j.inffus.2026.104291_bib0036","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/j.jclinepi.2006.01.014","article-title":"A gentle introduction to imputation of missing values","volume":"59","author":"Donders","year":"2006","journal-title":"J. Clin. Epidemiol."},{"issue":"10","key":"10.1016\/j.inffus.2026.104291_bib0037","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1080\/08839514.2019.1637138","article-title":"Comparison of performance of data imputation methods for numeric dataset","volume":"33","author":"Jadhav","year":"2019","journal-title":"Appl. Artif. Intell."},{"issue":"1","key":"10.1016\/j.inffus.2026.104291_bib0038","article-title":"Missing data imputation: focusing on single imputation","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann. Transl. Med."},{"key":"10.1016\/j.inffus.2026.104291_bib0039","series-title":"Contemporary Computing: Third International Conference, IC3 2010, Noida, India, August 9\u201311, 2010. Proceedings, Part I 3","first-page":"600","article-title":"Missing value imputation based on k-mean clustering with weighted distance","author":"Patil","year":"2010"},{"key":"10.1016\/j.inffus.2026.104291_bib0040","series-title":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility","first-page":"45","article-title":"Spatio-temporal clustering of traffic data with deep embedded clustering","author":"Asadi","year":"2019"},{"key":"10.1016\/j.inffus.2026.104291_bib0041","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.jss.2017.07.012","article-title":"Cross-validation based k nearest neighbor imputation for software quality datasets: an empirical study","volume":"132","author":"Huang","year":"2017","journal-title":"J. Syst. Software"},{"issue":"6","key":"10.1016\/j.inffus.2026.104291_bib0042","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1080\/03610910701569069","article-title":"On the use of adaptive nearest neighbors for missing value imputation","volume":"36","author":"Jhun","year":"2007","journal-title":"Commun. Stat.\u2013Simul. Comput.\u00ae"},{"key":"10.1016\/j.inffus.2026.104291_bib0043","series-title":"2015 4th International Conference on Computer Science and Network Technology (ICCSNT)","first-page":"94","article-title":"Iterative KNN imputation based on GRA for missing values in TPLMS","volume":"1","author":"Zhu","year":"2015"},{"issue":"4","key":"10.1016\/j.inffus.2026.104291_bib0044","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1080\/24725579.2019.1583704","article-title":"Nested Gaussian process modeling and imputation of high-dimensional incomplete data under uncertainty","volume":"9","author":"Imani","year":"2019","journal-title":"IISE Trans. Healthcare Syst. Eng."},{"issue":"2","key":"10.1016\/j.inffus.2026.104291_bib0045","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TITS.2018.2817879","article-title":"Multi-output Gaussian processes for crowdsourced traffic data imputation","volume":"20","author":"Rodrigues","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.inffus.2026.104291_bib0046","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.ins.2013.01.021","article-title":"A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm","volume":"233","author":"Aydilek","year":"2013","journal-title":"Inf. Sci."},{"key":"10.1016\/j.inffus.2026.104291_sbref0047","first-page":"1514","article-title":"Missing data: a comparison of neural network and expectation maximization techniques","author":"Nelwamondo","year":"2007","journal-title":"Curr. Sci."},{"key":"10.1016\/j.inffus.2026.104291_bib0048","series-title":"2018 10th International Conference on Knowledge and Systems Engineering (KSE)","first-page":"247","article-title":"Comparison of the most influential missing data imputation algorithms for healthcare","author":"Le","year":"2018"},{"issue":"5","key":"10.1016\/j.inffus.2026.104291_bib0049","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1080\/08839510902872223","article-title":"An empirical comparison of techniques for handling incomplete data using decision trees","volume":"23","author":"Twala","year":"2009","journal-title":"Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.inffus.2026.104291_bib0050","first-page":"13","article-title":"A comparative study of decision tree ID3 and C4. 5","volume":"4","author":"Hssina","year":"2014","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"10.1016\/j.inffus.2026.104291_bib0051","series-title":"Data Mining and Knowledge Discovery handbook","volume":"2","author":"Maimon","year":"2005"},{"issue":"8","key":"10.1016\/j.inffus.2026.104291_bib0052","doi-asserted-by":"crossref","DOI":"10.1093\/gigascience\/giaa082","article-title":"Genomic data imputation with variational auto-encoders","volume":"9","author":"Qiu","year":"2020","journal-title":"Gigascience"},{"key":"10.1016\/j.inffus.2026.104291_bib0053","series-title":"Advances in Intelligent Data Analysis XVII: 17th International Symposium, IDA 2018,\u2019s-Hertogenbosch, the Netherlands, October 24\u201326, 2018, Proceedings 17","first-page":"87","article-title":"Missing data imputation via denoising autoencoders: the untold story","author":"Costa","year":"2018"},{"issue":"1","key":"10.1016\/j.inffus.2026.104291_bib0054","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-018-34688-x","article-title":"AutoImpute: autoencoder based imputation of single-cell RNA-seq data","volume":"8","author":"Talwar","year":"2018","journal-title":"Sci. Rep."},{"key":"10.1016\/j.inffus.2026.104291_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2020.109941","article-title":"A bi-directional missing data imputation scheme based on LSTM and transfer learning for building energy data","volume":"216","author":"Ma","year":"2020","journal-title":"Energy Build."},{"key":"10.1016\/j.inffus.2026.104291_bib0056","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.neucom.2020.05.033","article-title":"Smoothed LSTM-AE: a spatio-temporal deep model for multiple time-series missing imputation","volume":"411","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.inffus.2026.104291_bib0057","series-title":"Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers","first-page":"1293","article-title":"Imputation of missing data in time series for air pollutants using long short-term memory recurrent neural networks","author":"Yuan","year":"2018"},{"key":"10.1016\/j.inffus.2026.104291_bib0058","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1080\/00182494.1976.10112639","article-title":"Record linkage","volume":"9","author":"Hershberg","year":"1976","journal-title":"Hist. Methods Newsletter"},{"key":"10.1016\/j.inffus.2026.104291_bib0059","series-title":"Proceedings of the 23rd International Conference on Extending Database Technology, EDBT 2020, Copenhagen, Denmark, March 30, - April 02, 2020","first-page":"647","article-title":"Entity resolution: past, present and yet-to-come","author":"Papadakis","year":"2020"},{"issue":"5","key":"10.1016\/j.inffus.2026.104291_bib0060","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1002\/wics.1317","article-title":"Matching and record linkage","volume":"6","author":"Winkler","year":"2014","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"issue":"1-2","key":"10.1016\/j.inffus.2026.104291_bib0061","doi-asserted-by":"crossref","first-page":"484","DOI":"10.14778\/1920841.1920904","article-title":"Evaluation of entity resolution approaches on real-world match problems","volume":"3","author":"K\u00f6pcke","year":"2010","journal-title":"Proc. VLDB Endowment"},{"key":"10.1016\/j.inffus.2026.104291_bib0062","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109660","article-title":"Multilingual entity alignment by abductive knowledge reasoning on multiple knowledge graphs","volume":"139","author":"Akhtar","year":"2025","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526001703?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526001703?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T15:45:59Z","timestamp":1777304759000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526001703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":62,"alternative-id":["S1566253526001703"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104291","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Semantic-aware data imputation in dynamic relational databases via pre-trained language models","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104291","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104291"}}