{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:02:30Z","timestamp":1771466550971,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032052803","type":"print"},{"value":"9783032052810","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05281-0_9","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T12:48:56Z","timestamp":1758199736000},"page":"131-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LSBlock: A Hybrid Blocking System Combining Lexical and\u00a0Semantic Similarity Search for\u00a0Record Linkage"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3878-5988","authenticated-orcid":false,"given":"Dimitrios","family":"Karapiperis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8263-9024","authenticated-orcid":false,"given":"Christos","family":"Tjortjis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9758-0819","authenticated-orcid":false,"given":"Vassilios","family":"Verykios","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Broder, A.Z., Charikar, M., Frieze, A., Mitzenmacher, M.: Minwise independent permutations. In: ACM STOC, pp. 327\u2013336 (1998)","DOI":"10.1145\/276698.276781"},{"key":"9_CR3","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures - a step forward in data integration. In: EDBT, pp. 463\u2013473 (2020)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, R., Shen, Y., Zhang, D.: GNEM: a generic one-to-set neural entity matching framework. In: WWW, pp. 1686\u20131694 (2020)","DOI":"10.1145\/3442381.3450119"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Christen, P.: Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Data-Centric Systems and Applications. Springer (2012)","DOI":"10.1007\/978-3-642-31164-2"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Christophides, V., Efthymiou, V., Stefanidis, K.: Entity Resolution in the Web of Data. Morgan & Claypool Publishers (2015)","DOI":"10.1007\/978-3-031-79468-1"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang., M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Ebraheem, M., Thirumuruganathan, S., Joty, S.R., Ouzzani, M., Tang, N.: Distributed representations of tuples for entity resolution. In: PVLDB, pp. 1454\u20131467 (2018)","DOI":"10.14778\/3236187.3269461"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Gagliardelli, L., Papadakis, G., Simonini, G., Bergamaschi, S., Palpanas, T.: GSM: a generalized approach to supervised meta-blocking for scalable entity resolution. Inf. Syst. 120 (2024)","DOI":"10.1016\/j.is.2023.102307"},{"key":"9_CR10","unstructured":"Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: VLDB, pp. 518\u2013529 (1999)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Karapiperis, D., Tjortjis, C., Verykios, V.: A randomized blocking structure for streaming record linkage. In: PVLDB, pp. 2783\u20132791 (2023)","DOI":"10.14778\/3611479.3611487"},{"issue":"7","key":"9_CR12","first-page":"2803","volume":"36","author":"D Karapiperis","year":"2024","unstructured":"Karapiperis, D., Tjortjis, C., Verykios, V.: A suite of efficient randomized algorithms for streaming record linkage. TKDE 36(7), 2803\u20132813 (2024)","journal-title":"TKDE"},{"issue":"4","key":"9_CR13","first-page":"909","volume":"27","author":"D Karapiperis","year":"2015","unstructured":"Karapiperis, D., Verykios, V.: An LSH-based blocking approach with a homomorphic matching technique for privacy-preserving record linkage. TKDE 27(4), 909\u2013921 (2015)","journal-title":"TKDE"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, J., Suhara, Y., Doan, A., Tan, W.C.: Deep entity matching with pre-trained language models. In: PVLDB, pp. 50\u201360 (2020)","DOI":"10.14778\/3421424.3421431"},{"key":"9_CR15","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"9_CR16","unstructured":"Lundberg, S., Lee, S.: A unified approach to interpreting model predictions. In: NIPS, pp. 4768\u20134777 (2017)"},{"issue":"4","key":"9_CR17","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","volume":"42","author":"Y Malkov","year":"2018","unstructured":"Malkov, Y., Yashunin, D.: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 824\u2013836 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR18","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arxiv:1301.3781 (2013)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Mudgal, S., et al.: Deep learning for entity matching: a design space exploration. In: SIGMOD, pp. 19\u201334 (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"O\u2019hare, K., Jurek-Loughrey, A., Campos, C.D.: High-value token-blocking: efficient blocking method for record linkage. TKDD 16(2), 1\u201317 (2021)","DOI":"10.1145\/3450527"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Alexiou, G., Papastefanatos, G., Koutrika, G.: Schema-agnostic vs schema-based configurations for blocking methods on homogeneous data. In: PVLDB, pp. 315\u2013323 (2015)","DOI":"10.14778\/2856318.2856326"},{"issue":"8","key":"9_CR22","first-page":"1946","volume":"26","author":"G Papadakis","year":"2014","unstructured":"Papadakis, G., Koutrika, G., Palpanas, T., Nejdl, W.: Meta-blocking: taking entity resolution to the next level. TKDE 26(8), 1946\u20131960 (2014)","journal-title":"TKDE"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Papastefanatos, G., Koutrika, G.: Supervised meta-blocking. In: PVLDB, pp. 1929\u20131940 (2014)","DOI":"10.14778\/2733085.2733098"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Svirsky, J., Gal, A., Palpanas, T.: Comparative analysis of approximate blocking techniques for entity resolution. In: PVLDB, pp. 684\u2013695 (2016)","DOI":"10.14778\/2947618.2947624"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Paulsen, D., Govind, Y., Doan, A.: Sparkly: a simple yet surprisingly strong TF\/IDF blocker for entity matching. In: PVLDB, pp. 1507\u20131519 (2023)","DOI":"10.14778\/3583140.3583163"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: EMNLP-IJCNLP, pp. 3980\u20133990 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"9_CR28","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Thirumuruganathan, S., et al.: Deep learning for blocking in entity matching: a design space exploration. In: PVLDB, pp. 2459\u20132472 (2021)","DOI":"10.14778\/3476249.3476294"},{"issue":"2","key":"9_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1921632.1921635","volume":"5","author":"T de Vries","year":"2011","unstructured":"de Vries, T., Ke, H., Chawla, S., Christen, P.: Robust record linkage blocking using suffix arrays and bloom filters. TKDD 5(2), 1\u201327 (2011)","journal-title":"TKDD"},{"key":"9_CR31","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Zeakis, A., Papadakis, G., Skoutas, D., Koubarakis, M.: Pre-trained embeddings for entity resolution an experimental analysis. In: PVLDB, pp. 2225\u20132238 (2023)","DOI":"10.14778\/3598581.3598594"},{"issue":"9","key":"9_CR33","first-page":"2225","volume":"16","author":"A Zeakis","year":"2023","unstructured":"Zeakis, A., Papadakis, G., Skoutas, D., Koubarakis, M.: Pre-trained embeddings for entity resolution: an experimental analysis. PVLDB 16(9), 2225\u20132238 (2023)","journal-title":"PVLDB"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wei, H., Sisman, B., Dong, X.L., Faloutsos, C., Page, D.: Autoblock: a hands-off blocking framework for entity matching. In: WSDM, pp. 744\u2013752 (2020)","DOI":"10.1145\/3336191.3371813"}],"container-title":["Lecture Notes in Computer Science","Advances in Databases and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05281-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T12:56:25Z","timestamp":1767876985000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05281-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"ISBN":["9783032052803","9783032052810"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05281-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"assertion":[{"value":"18 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADBIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Advances in Databases and Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tampere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adbis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adbis2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}