{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:51:47Z","timestamp":1781877107107,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819538263","type":"print"},{"value":"9789819538270","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\/978-981-95-3827-0_12","type":"book-chapter","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:03:53Z","timestamp":1781874233000},"page":"182-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Subset Discovery for\u00a0Entity Matching"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yafeng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoou","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bogatu, A., Paton, N.W., Douthwaite, M., Davie, S., Freitas, A.: Cost\u2013effective variational active entity resolution. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 1272\u20131283 (2021)","DOI":"10.1109\/ICDE51399.2021.00114"},{"key":"12_CR2","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures - a step forward in data integration. In: International Conference on Extending Database Technology (2020)"},{"key":"12_CR3","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures - a step forward in data integration. OpenProceedings (2020)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chai, C., Li, G., Li, J., Deng, D., Feng, J.: A partial-order-based framework for cost-effective crowdsourced entity resolution. The VLDB J. 27 (12 2018)","DOI":"10.1007\/s00778-018-0509-6"},{"key":"12_CR5","unstructured":"Chaudhuri, S., Chen, B.C., Ganti, V., Kaushik, R.: Example-driven design of efficient record matching queries. In: Proceedings of the 33rd International Conference on Very Large Data Bases, pp. 327\u2013338. VLDB \u201907, VLDB Endowment (2007)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Tang, N., Fan, J., Yan, X., Chai, C., Li, G., Du, X.: Haipipe: Combining human-generated and machine-generated pipelines for data preparation. Proc. ACM Manag. Data 1(1), May 2023","DOI":"10.1145\/3588945"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"Chen, S., Ding, X., Liang, Z., Tang, Y., Wang, H.: Hyper-parameter recommendation for truth discovery. In: Onizuka, M., et al. (eds.) DASFAA 2024, Part III. LNCS, vol. 14852, pp. 277\u2013292. Springer (2024). https:\/\/doi.org\/10.1007\/978-981-97-5555-4_18","DOI":"10.1007\/978-981-97-5555-4_18"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Das, S., et al.: Falcon: Scaling up hands-off crowdsourced entity matching to build cloud services. In: Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD \u201917, pp. 1431\u20131446. Association for Computing Machinery, New York (2017)","DOI":"10.1145\/3035918.3035960"},{"issue":"11","key":"12_CR9","doi-asserted-by":"publisher","first-page":"3484","DOI":"10.14778\/3681954.3682015","volume":"17","author":"X Ding","year":"2024","unstructured":"Ding, X., Lu, Y., Wang, H., Wang, C., Liu, Y., Wang, J.: Dafdiscover: robust mining algorithm for dynamic approximate functional dependencies on dirty data. Proc. VLDB Endow. 17(11), 3484\u20133496 (2024)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Ding, X., Wang, H., Su, J., Wang, M., Li, J., Gao, H.: Leveraging currency for repairing inconsistent and incomplete data. IEEE Trans. Knowl. Data Eng. 34(3), 1288\u20131302 (2022). https:\/\/doi.org\/10.1109\/TKDE.2020.2992456","DOI":"10.1109\/TKDE.2020.2992456"},{"key":"12_CR11","volume-title":"Principles of Data Integration","author":"A Doan","year":"2012","unstructured":"Doan, A., Halevy, A., Ives, Z.: Principles of Data Integration, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco (2012)","edition":"1"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Ebaid, A., Thirumuruganathan, S., Aref, W.G., Elmagarmid, A., Ouzzani, M.: Explainer: entity resolution explanations. In: 2019 IEEE 35th International Conference on Data Engineering (ICDE), pp. 2000\u20132003 (2019)","DOI":"10.1109\/ICDE.2019.00224"},{"issue":"11","key":"12_CR13","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.14778\/3236187.3236198","volume":"11","author":"M Ebraheem","year":"2018","unstructured":"Ebraheem, M., Thirumuruganathan, S., Joty, S., Ouzzani, M., Tang, N.: Distributed representations of tuples for entity resolution. Proc. VLDB Endow. 11(11), 1454\u20131467 (2018)","journal-title":"Proc. VLDB Endow."},{"issue":"406","key":"12_CR14","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. J. Am. Stat. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"J. Am. Stat. Assoc."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Kang, R., Song, S., Wang, C.: Conditional regression rules. In: 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp. 2481\u20132493 (2022)","DOI":"10.1109\/ICDE53745.2022.00231"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Konda, P., et al.: Magellan: toward building entity matching management systems. Proc. VLDB Endow. 9(12), 1197\u20131208 (2016)","DOI":"10.14778\/2994509.2994535"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Li, P., Cheng, X., Chu, X., He, Y., Chaudhuri, S.: Auto-fuzzyjoin: Auto-program fuzzy similarity joins without labeled examples. In: Proceedings of the 2021 International Conference on Management of Data, SIGMOD \u201921, pp. 1064\u20131076. Association for Computing Machinery, New York (2021)","DOI":"10.1145\/3448016.3452824"},{"issue":"1","key":"12_CR18","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 Endow. 14(1), 50\u201360 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Li, Z., Ding, X., Wang, H.: An effective constraint-based anomaly detection approach on multivariate time series. In: Wang, X., Zhang, R., Lee, Y., Sun, L., Moon, Y. (eds.) APWeb-WAIM 2020, Part II. LNCS, vol. 12318, pp. 61\u201369. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-60290-1_5","DOI":"10.1007\/978-3-030-60290-1_5"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Liang, Z., Wang, H., Ding, X., Mu, T.: Industrial time series determinative anomaly detection based on constraint hypergraph. Know.-Based Syst. 233(C), December 2021. https:\/\/doi.org\/10.1016\/j.knosys.2021.107548","DOI":"10.1016\/j.knosys.2021.107548"},{"key":"12_CR21","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, SIGMOD \u201921, pp. 1303\u20131316. Association for Computing Machinery, New York (2021)","DOI":"10.1145\/3448016.3457258"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"M.K, V., K., K.: A survey on similarity measures in text mining (2016)","DOI":"10.5121\/mlaij.2016.3103"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Mudgal, S., Li, H., Rekatsinas, T., Doan, A., Park, Y., Krishnan, G., Deep, R., Arcaute, E., Raghavendra, V.: Deep learning for entity matching: a design space exploration. In: Proceedings of the 2018 International Conference on Management of Data, SIGMOD \u201918, pp. 19\u201334. Association for Computing Machinery, New York (2018)","DOI":"10.1145\/3183713.3196926"},{"issue":"10","key":"12_CR24","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.14778\/3467861.3467878","volume":"14","author":"R Peeters","year":"2021","unstructured":"Peeters, R., Bizer, C.: Dual-objective fine-tuning of bert for entity matching. Proc. VLDB Endow. 14(10), 1913\u20131921 (2021)","journal-title":"Proc. VLDB Endow."},{"issue":"11","key":"12_CR25","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.14778\/3611479.3611525","volume":"16","author":"N Shahbazi","year":"2023","unstructured":"Shahbazi, N., Danevski, N., Nargesian, F., Asudeh, A., Srivastava, D.: Through the fairness lens: Experimental analysis and evaluation of entity matching. Proc. VLDB Endow. 16(11), 3279\u20133292 (2023)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Shahbazi, N., Wang, J., Miao, Z., Bhutani, N.: Fairness-aware data preparation for entity matching. In: 2024 IEEE 40th International Conference on Data Engineering (ICDE), pp. 3476\u20133489 (2024)","DOI":"10.1109\/ICDE60146.2024.00268"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Steorts, R.C., Ventura, S.L., Sadinle, M., Fienberg, S.E.: A comparison of blocking methods for record linkage. In: Privacy in Statistical Databases (2014)","DOI":"10.1007\/978-3-319-11257-2_20"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Tu, J., et al.: Unicorn: a unified multi-tasking model for supporting matching tasks in data integration. Proc. ACM Manag. Data 1(1) (May 2023)","DOI":"10.1145\/3588938"},{"issue":"12","key":"12_CR29","doi-asserted-by":"publisher","first-page":"3666","DOI":"10.14778\/3554821.3554870","volume":"15","author":"J Tu","year":"2022","unstructured":"Tu, J., Han, X., Fan, J., Tang, N., Chai, C., Li, G., Du, X.: Dader: hands-off entity resolution with domain adaptation. Proc. VLDB Endow. 15(12), 3666\u20133669 (2022)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Wang, H., Ding, X., Li, J., Gao, H.: Rule-based entity resolution on database with hidden temporal information. IEEE Trans. Knowl. Data Eng. 30(11), 2199\u20132212 (2018). https:\/\/doi.org\/10.1109\/TKDE.2018.2816018","DOI":"10.1109\/TKDE.2018.2816018"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Wang, P., Zheng, W., Wang, J., Pei, J.: Automating entity matching model development. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 1296\u20131307 (2021)","DOI":"10.1109\/ICDE51399.2021.00116"},{"key":"12_CR32","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)","DOI":"10.1109\/ICDE55515.2023.00391"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Wu, R., Chaba, S., Sawlani, S., Chu, X., Thirumuruganathan, S.: Zeroer: entity resolution using zero labeled examples. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD \u201920, pp. 1149\u20131164. Association for Computing Machinery, New York (2020)","DOI":"10.1145\/3318464.3389743"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3827-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:04:06Z","timestamp":1781874246000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3827-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819538263","9789819538270"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3827-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"20 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","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":"26 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2025.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}