{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T04:58:15Z","timestamp":1790139495055,"version":"4.0.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032190956","type":"print"},{"value":"9783032190963","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-19096-3_37","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:17:42Z","timestamp":1778365062000},"page":"554-566","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Domain-Constrained Data Augmentation for\u00a0Entity Resolution"],"prefix":"10.1007","author":[{"given":"Marco","family":"Napoleone","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Console","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurizio","family":"Lenzerini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Merialdo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Papi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonella","family":"Poggi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Scafoglieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Torlone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"37_CR1","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures-a step forward in data integration. In: International Conference on Extending Database Technology, Copenhagen, 30 March-2 April 2020 (2020)"},{"issue":"2","key":"37_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3696206","volume":"57","author":"C Cao","year":"2024","unstructured":"Cao, C., Zhou, F., Dai, Y., Wang, J., Zhang, K.: A survey of mix-based data augmentation: taxonomy, methods, applications, and explainability. ACM Comput. Surv. 57(2), 1\u201338 (2024)","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"37_CR3","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.: An overview of end-to-end entity resolution for big data. ACM Comput. Surv. (CSUR) 53(6), 1\u201342 (2020)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"37_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108098","volume":"119","author":"GH De Rosa","year":"2021","unstructured":"De Rosa, G.H., Papa, J.P.: A survey on text generation using generative adversarial networks. Pattern Recogn. 119, 108098 (2021)","journal-title":"Pattern Recogn."},{"key":"37_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"37_CR7","unstructured":"Ebraheem, M., Thirumuruganathan, S., Joty, S., Ouzzani, M., Tang, N.: Deeper\u2013deep entity resolution. arXiv preprint arXiv:1710.00597 (2017)"},{"issue":"1","key":"37_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2006","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2006)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"37_CR9","doi-asserted-by":"publisher","unstructured":"Fagin, R., Kolaitis, P.G., Lembo, D., Popa, L., Scafoglieri, F.: A framework for combining entity resolution and query answering in knowledge bases. In: Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning, pp. 229\u2013239 (2023). https:\/\/doi.org\/10.24963\/kr.2023\/23","DOI":"10.24963\/kr.2023\/23"},{"key":"37_CR10","unstructured":"Fagin, R., Kolaitis, P.G., Lembo, D., Popa, L., Scafoglieri, F.: Combining entity resolution and query answering in ontologies: a formal conceptual framework. In: Proceedings of the 32nd Symposium of Advanced Database Systems, Villasimius, Italy, June 23rd to 26th, 2024. CEUR Workshop Proceedings, vol.\u00a03741, pp. 633\u2013642. CEUR-WS.org (2024). https:\/\/ceur-ws.org\/Vol-3741\/paper38.pdf"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Fan, M., et al.: Cost-effective in-context learning for entity resolution: a design space exploration. In: 2024 IEEE 40th International Conference on Data Engineering (ICDE), pp. 3696\u20133709. IEEE (2024)","DOI":"10.1109\/ICDE60146.2024.00284"},{"issue":"4","key":"37_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2567657","volume":"4","author":"W Fan","year":"2014","unstructured":"Fan, W., Ma, S., Tang, N., Yu, W.: Interaction between record matching and data repairing. J. Data Inf. Qual. (JDIQ) 4(4), 1\u201338 (2014)","journal-title":"J. Data Inf. Qual. (JDIQ)"},{"key":"37_CR13","unstructured":"Hussein, M.M.A.: LLM-enhanced entity matching: comparative analysis of traditional and modern techniques. Master\u2019s thesis, ETH Zurich (2025)"},{"key":"37_CR14","unstructured":"Jarke, M., Lenzerini, M., Vassiliou, Y., Vassiliadis, P.: Fundamentals of data warehouses. Springer Science and Business Media (2013)"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Konda, P., et\u00a0al.: Magellan: toward building entity matching management systems. Proc. VLDB Endowment 9(12), 1197\u20131208 (2016)","DOI":"10.14778\/2994509.2994535"},{"key":"37_CR16","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-032-08623-5_6","volume-title":"Conceptual Modeling","author":"D Lembo","year":"2026","unstructured":"Lembo, D., Lenzerini, M., Poggi, A., Scafoglieri, F.M.: Enriching ontology-based data management with multidimensional modeling. In: Bork, D., Lukyanenko, R., Sadiq, S., Bellatreche, L., Pastor, O. (eds.) Conceptual Modeling, pp. 106\u2013124. Springer Nature Switzerland, Cham (2026)"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Li, H., Feng, L., Li, S., Hao, F., Zhang, C.J., Song, Y.: On leveraging large language models for enhancing entity resolution: a cost-efficient approach. arXiv preprint arXiv:2401.03426 (2024)","DOI":"10.1145\/3589335.3651245"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Booster: leveraging large language models for enhancing entity resolution. In: Companion Proceedings of the ACM Web Conference 2024, pp. 1043\u20131046 (2024)","DOI":"10.1145\/3589335.3651245"},{"issue":"6","key":"37_CR20","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.: Effective entity matching with transformers. VLDB J. 32(6), 1215\u20131235 (2023)","journal-title":"VLDB J."},{"key":"37_CR21","doi-asserted-by":"publisher","first-page":"50","DOI":"10.14778\/3421424.3421431","volume":"14","author":"Y Li","year":"2020","unstructured":"Li, Y., Li, J., Suhara, Y., Doan, A., Tan, W.C.: Deep entity matching with pre-trained language models. Proc. VLDB Endowment 14, 50\u201360 (2020)","journal-title":"Proc. VLDB Endowment"},{"key":"37_CR22","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019), http:\/\/arxiv.org\/abs\/1907.11692"},{"issue":"2","key":"37_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3665930","volume":"16","author":"G Mecca","year":"2024","unstructured":"Mecca, G., Papotti, P., Santoro, D., Veltri, E.: Bunni: learning repair actions in rule-driven data cleaning. ACM J. Data Inf. Qual. 16(2), 1\u201331 (2024)","journal-title":"ACM J. Data Inf. Qual."},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Miao, Z., Li, Y., Wang, X.: Rotom: A meta-learned data augmentation framework for entity matching, data cleaning, text classification, and beyond. In: Proceedings of the 2021 International Conference on Management of Data, pp. 1303\u20131316 (2021)","DOI":"10.1145\/3448016.3457258"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Miao, Z., Li, Y., Wang, X., Tan, W.C.: Snippext: semi-supervised opinion mining with augmented data. In: Proceedings of The Web Conference 2020, pp. 617\u2013628 (2020)","DOI":"10.1145\/3366423.3380144"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Mudgal, S., et al.: Deep learning for entity matching: a design space exploration. In: Proceedings of the 2018 International Conference on Management of Data, pp. 19\u201334 (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Nananukul, N., Sisaengsuwanchai, K., Kejriwal, M.: Cost-efficient prompt engineering for unsupervised entity resolution. arXiv preprint arXiv:2310.06174 (2023)","DOI":"10.21203\/rs.3.rs-4177791\/v1"},{"issue":"2","key":"37_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-01878-7","volume":"16","author":"G Papadakis","year":"2021","unstructured":"Papadakis, G., Ioannou, E., Thanos, E., Palpanas, T.: The four generations of entity resolution. Synth. Lect. Data Manag. 16(2), 1\u2013170 (2021)","journal-title":"Synth. Lect. Data Manag."},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Peeters, R., Bizer, C.: Dual-objective fine-tuning of BERT for entity matching. Proc. VLDB Endow. 14(10), 1913\u20131921 (2021). http:\/\/www.vldb.org\/pvldb\/vol14\/p1913-peeters.pdf","DOI":"10.14778\/3467861.3467878"},{"key":"37_CR30","unstructured":"Peeters, R., Steiner, A., Bizer, C.: Entity matching using large language models. arXiv preprint arXiv:2310.11244 (2023)"},{"issue":"140","key":"37_CR31","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"37_CR32","doi-asserted-by":"publisher","first-page":"3666","DOI":"10.14778\/3554821.3554870","volume":"15","author":"J Tu","year":"2022","unstructured":"Tu, J., et al.: Dader: hands-off entity resolution with domain adaptation. Proc. VLDB Endow. 15(12), 3666\u20133669 (2022)","journal-title":"Proc. VLDB Endow."},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: Eda: Easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6382\u20136388 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"37_CR34","first-page":"6256","volume":"33","author":"Q Xie","year":"2020","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. Adv. Neural. Inf. Process. Syst. 33, 6256\u20136268 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: Adversarial domain adaptation with domain mixup. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a034, pp. 6502\u20136509 (2020)","DOI":"10.1609\/aaai.v34i04.6123"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19096-3_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:17:45Z","timestamp":1778365065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19096-3_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032190956","9783032190963"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19096-3_37","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}