{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T07:03:35Z","timestamp":1784876615637,"version":"3.55.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s10044-026-01744-6","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T06:48:56Z","timestamp":1784875736000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing blocking for entity matching with pre-trained language model and masked autoencoder"],"prefix":"10.1007","volume":"29","author":[{"given":"Zelin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"issue":"328","key":"1744_CR1","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi IP, Sunter AB (1969) A theory for record linkage. J Am Stat Assoc 64(328):1183\u20131210","journal-title":"J Am Stat Assoc"},{"issue":"3","key":"1744_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3442200","volume":"15","author":"N Barlaug","year":"2021","unstructured":"Barlaug N, Gulla JA (2021) Neural networks for entity matching: a survey. ACM Trans Knowl Discov Data (TKDD) 15(3):1\u201337","journal-title":"ACM Trans Knowl Discov Data (TKDD)"},{"issue":"9","key":"1744_CR3","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2011","unstructured":"Christen P (2011) A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans Knowl Data Eng 24(9):1537\u20131555","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"6","key":"1744_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2020","unstructured":"Christophides V, Efthymiou V, Palpanas T, Papadakis G, Stefanidis K (2020) An overview of end-to-end entity resolution for big data. ACM Comput Surv (CSUR) 53(6):1\u201342","journal-title":"ACM Comput Surv (CSUR)"},{"issue":"2","key":"1744_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377455","volume":"53","author":"G Papadakis","year":"2020","unstructured":"Papadakis G, Skoutas D, Thanos E, Palpanas T (2020) Blocking and filtering techniques for entity resolution: A survey. ACM Comput Surv (CSUR) 53(2):1\u201342","journal-title":"ACM Comput Surv (CSUR)"},{"key":"1744_CR6","doi-asserted-by":"crossref","unstructured":"O\u2019Hare K, Jurek-Loughrey A, Campos Cd (2019) A review of unsupervised and semi-supervised blocking methods for record linkage. in: Linking and mining heterogeneous and multi-view data, pp 79\u2013105","DOI":"10.1007\/978-3-030-01872-6_4"},{"issue":"9","key":"1744_CR7","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.14778\/3598581.3598594","volume":"16","author":"A Zeakis","year":"2023","unstructured":"Zeakis A, Papadakis G, Skoutas D, Koubarakis M (2023) Pre-trained embeddings for entity resolution: an experimental analysis. Proc VLDB Endow 16(9):2225\u20132238","journal-title":"Proc VLDB Endow"},{"key":"1744_CR8","doi-asserted-by":"crossref","unstructured":"Papadakis G, Ioannou E, Nieder\u00e9e C, Fankhauser P (2011) Efficient entity resolution for large heterogeneous information spaces. In: Proceedings of the Fourth ACM International Conference on web search and data mining, pp 535\u2013544","DOI":"10.1145\/1935826.1935903"},{"issue":"11","key":"1744_CR9","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.14778\/3476249.3476294","volume":"14","author":"S Thirumuruganathan","year":"2021","unstructured":"Thirumuruganathan S, Li H, Tang N, Ouzzani M, Govind Y, Paulsen D, Fung G, Doan A (2021) Deep learning for blocking in entity matching: a design space exploration. Proc VLDB Endow 14(11):2459\u20132472","journal-title":"Proc VLDB Endow"},{"key":"1744_CR10","unstructured":"Michelson M, Knoblock CA (2006) Learning blocking schemes for record linkage, vol 6. In: AAAI, pp 440\u2013445"},{"key":"1744_CR11","doi-asserted-by":"crossref","unstructured":"Javdani D, Rahmani H, Allahgholi M, Karimkhani F (2019) Deepblock: a novel blocking approach for entity resolution using deep learning. In: 2019 5th International Conference on web research (ICWR). IEEE, pp 41\u201344","DOI":"10.1109\/ICWR.2019.8765267"},{"key":"1744_CR12","doi-asserted-by":"crossref","unstructured":"Zhang W, Wei H, Sisman B, Dong XL, Faloutsos C, Page D (2020) Autoblock: A hands-off blocking framework for entity matching. In: Proceedings of the 13th International Conference on web search and data mining, pp 744\u2013752","DOI":"10.1145\/3336191.3371813"},{"issue":"14","key":"1744_CR13","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.14778\/2733085.2733098","volume":"7","author":"G Papadakis","year":"2014","unstructured":"Papadakis G, Papastefanatos G, Koutrika G (2014) Supervised meta-blocking. Proc VLDB Endow 7(14):1929\u20131940","journal-title":"Proc VLDB Endow"},{"key":"1744_CR14","doi-asserted-by":"crossref","unstructured":"Bilenko M, Kamath B, Mooney RJ (2006) Adaptive blocking: Learning to scale up record linkage. In: Sixth International Conference on Data Mining (ICDM\u201906). IEEE, pp 87\u201396","DOI":"10.1109\/ICDM.2006.13"},{"key":"1744_CR15","doi-asserted-by":"crossref","unstructured":"Brinkmann A, Shraga R, Bizer C (2024) Sc-block: supervised contrastive blocking within entity resolution pipelines. In: European Semantic Web Conference. Springer, pp 121\u2013142","DOI":"10.1007\/978-3-031-60626-7_7"},{"key":"1744_CR16","doi-asserted-by":"crossref","unstructured":"Wang, R., Li, Y., Wang, J.: Sudowoodo: contrastive self-supervised learning for multi-purpose data integration and preparation. In: 2023 IEEE 39th International Conference on data engineering (ICDE), pp. 1502\u20131515 (2023). IEEE","DOI":"10.1109\/ICDE55515.2023.00391"},{"key":"1744_CR17","doi-asserted-by":"crossref","unstructured":"Yao D, Gu Y, Cong G, Jin H, Lv X (2022) Entity resolution with hierarchical graph attention networks. In: Proceedings of the 2022 International Conference on management of data. pp 429\u2013442","DOI":"10.1145\/3514221.3517872"},{"issue":"1","key":"1744_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3431816","volume":"13","author":"Y Li","year":"2021","unstructured":"Li Y, Li J, Suhara Y, Wang J, Hirota W, Tan W-C (2021) Deep entity matching: challenges and opportunities. J Data Inform Qual (JDIQ) 13(1):1\u201317","journal-title":"J Data Inform Qual (JDIQ)"},{"issue":"12","key":"1744_CR19","doi-asserted-by":"publisher","first-page":"12139","DOI":"10.1109\/TKDE.2021.3134806","volume":"35","author":"C Ge","year":"2021","unstructured":"Ge C, Wang P, Chen L, Liu X, Zheng B, Gao Y (2021) Collaborem: a self-supervised entity matching framework using multi-features collaboration. IEEE Trans Knowl Data Eng 35(12):12139\u201312152","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1744_CR20","doi-asserted-by":"crossref","unstructured":"Li Y, Li J, Suhara Y, Doan A, Tan W-C (2020) Deep entity matching with pre-trained language models. arXiv preprint arXiv:2004.00584","DOI":"10.14778\/3421424.3421431"},{"issue":"6","key":"1744_CR21","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1007\/s00778-023-00779-z","volume":"32","author":"Y Li","year":"2023","unstructured":"Li Y, Li J, Suhara Y, Doan A, Tan W-C (2023) Effective entity matching with transformers. VLDB J 32(6):1215\u20131235","journal-title":"VLDB J"},{"key":"1744_CR22","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.14778\/3467861.3467878","volume":"14","author":"R Peeters","year":"2021","unstructured":"Peeters R, Bizer C (2021) Dual-objective fine-tuning of Bert for entity matching. Proc VLDB Endow 14:1913\u20131921","journal-title":"Proc VLDB Endow"},{"issue":"12","key":"1744_CR23","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1109\/TKDE.2012.150","volume":"25","author":"G Papadakis","year":"2012","unstructured":"Papadakis G, Ioannou E, Palpanas T, Nieder\u00e9e C, Nejdl W (2012) A blocking framework for entity resolution in highly heterogeneous information spaces. IEEE Trans Knowl Data Eng 25(12):2665\u20132682","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"1744_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2006","unstructured":"Elmagarmid AK, Ipeirotis PG, Verykios VS (2006) Duplicate record detection: a survey. IEEE Trans Knowl Data Eng 19(1):1\u201316","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1744_CR25","volume-title":"An introduction to duplicate detection","author":"F Nauman","year":"2022","unstructured":"Nauman F, Herschel M (2022) An introduction to duplicate detection. Springer, Berlin"},{"issue":"6","key":"1744_CR26","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.14778\/3583140.3583163","volume":"16","author":"D Paulsen","year":"2023","unstructured":"Paulsen D, Govind Y, Doan A (2023) Sparkly: a simple yet surprisingly strong tf\/idf blocker for entity matching. Proc VLDB Endow 16(6):1507\u20131519","journal-title":"Proc VLDB Endow"},{"key":"1744_CR27","unstructured":"Papadakis G, Fisichella M, Schoger F, Mandilaras G, Augsten N, Nejdl W (2022) How to reduce the search space of entity resolution: with blocking or nearest neighbor search? arXiv preprint arXiv:2202.12521"},{"key":"1744_CR28","unstructured":"Ebraheem M, Thirumuruganathan S, Joty S, Ouzzani M, Tang N (2017) Deeper-deep entity resolution. arXiv preprint arXiv:1710.00597"},{"issue":"1","key":"1744_CR29","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s00778-022-00745-1","volume":"32","author":"J Huang","year":"2023","unstructured":"Huang J, Hu W, Bao Z, Chen Q, Qu Y (2023) Deep entity matching with adversarial active learning. VLDB J 32(1):229\u2013255","journal-title":"VLDB J"},{"key":"1744_CR30","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1744_CR31","unstructured":"Arora S, Liang Y, Ma T (2017) A simple but tough-to-beat baseline for sentence embeddings. In: International Conference on learning representations"},{"key":"1744_CR32","doi-asserted-by":"crossref","unstructured":"Mudgal S, Li H, Rekatsinas T, Doan A, Park Y, Krishnan G, Deep R, Arcaute E, Raghavendra V (2018) Deep learning for entity matching: a design space exploration. In: Proceedings of the 2018 International Conference on management of data, pp 19\u201334","DOI":"10.1145\/3183713.3196926"},{"key":"1744_CR33","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"3","key":"1744_CR34","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson J, Douze M, J\u00e9gou H (2019) Billion-scale similarity search with gpus. IEEE Trans Big Data 7(3):535\u2013547","journal-title":"IEEE Trans Big Data"},{"key":"1744_CR35","unstructured":"Li H, Konda P, GC PS, Doan A, Snyder B, Park Y, Krishnan G, Deep R, Raghavendra V (2018) Matchcatcher: a debugger for blocking in entity matching. In: EDBT, pp. 193\u2013204"},{"key":"1744_CR36","unstructured":"Kenton JDM-WC, Toutanova LK (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol. 1, p. 2"},{"key":"1744_CR37","unstructured":"Liu Y (2019) Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"1744_CR38","doi-asserted-by":"crossref","unstructured":"Dogra V, Singh A, Verma S, Kavita, Jhanjhi N, Talib M (2021) Analyzing Distilbert for sentiment classification of banking financial news. In: Intelligent Computing and Innovation on Data Science: Proceedings of ICTIDS 2021. Springer, pp 501\u2013510","DOI":"10.1007\/978-981-16-3153-5_53"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01744-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01744-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01744-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T06:49:06Z","timestamp":1784875746000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01744-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["1744"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01744-6","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"3 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"155"}}