{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:41:22Z","timestamp":1757310082268},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319684734"},{"type":"electronic","value":"9783319684741"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-68474-1_20","type":"book-chapter","created":{"date-parts":[[2017,9,27]],"date-time":"2017-09-27T11:15:48Z","timestamp":1506510948000},"page":"284-299","source":"Crossref","is-referenced-by-count":7,"title":["DS-Prox: Dataset Proximity Mining for Governing the Data Lake"],"prefix":"10.1007","author":[{"given":"Ayman","family":"Alserafi","sequence":"first","affiliation":[]},{"given":"Toon","family":"Calders","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Abell\u00f3","sequence":"additional","affiliation":[]},{"given":"Oscar","family":"Romero","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,28]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","unstructured":"Abell\u00f3, A.: Big data design. In: Proceedings of ACM DOLAP, pp. 35\u201338 (2015). doi: 10.1145\/2811222.2811235","DOI":"10.1145\/2811222.2811235"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Alserafi, A., Abell\u00f3, A., Romero, O., Calders, T.: Towards information profiling: data lake content metadata management. In: DINA Workshop, ICDM (2016). doi: 10.1109\/ICDMW.2016.0033","DOI":"10.1109\/ICDMW.2016.0033"},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-642-32153-5_6","volume-title":"Similarity Search and Applications","author":"LG Ares","year":"2012","unstructured":"Ares, L.G., Brisaboa, N.R., Ord\u00f3\u00f1ez Pereira, A., Pedreira, O.: Efficient similarity search in metric spaces with cluster reduction. In: Navarro, G., Pestov, V. (eds.) SISAP 2012. LNCS, vol. 7404, pp. 70\u201384. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-32153-5_6"},{"issue":"11","key":"20_CR4","doi-asserted-by":"crossref","first-page":"695","DOI":"10.14778\/3402707.3402710","volume":"4","author":"PA Bernstein","year":"2011","unstructured":"Bernstein, P.A., Madhavan, J., Rahm, E.: Generic schema matching, ten years later. Proc. VLDB Endowment 4(11), 695\u2013701 (2011)","journal-title":"Proc. VLDB Endowment"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: ACM SIGKDD, pp. 39\u201348 (2003)","DOI":"10.1145\/956750.956759"},{"key":"20_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-319-11988-5_24","volume-title":"Similarity Search and Applications","author":"JA Cordero Cruz","year":"2014","unstructured":"Cordero Cruz, J.A., Garza, S.E., Schaeffer, S.E.: Entity recognition for duplicate filtering. In: Traina, A.J.M., Traina, C., Cordeiro, R.L.F. (eds.) SISAP 2014. LNCS, vol. 8821, pp. 253\u2013264. Springer, Cham (2014). doi: 10.1007\/978-3-319-11988-5_24"},{"issue":"3","key":"20_CR7","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1023\/B:MACH.0000015881.36452.6e","volume":"54","author":"S D\u017eeroski","year":"2004","unstructured":"D\u017eeroski, S., \u017denko, B.: Is combining classifiers with stacking better than selecting the best one? Mach. Learn. 54(3), 255\u2013273 (2004)","journal-title":"Mach. Learn."},{"key":"20_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-642-41062-8_6","volume-title":"Similarity Search and Applications","author":"K Figueroa","year":"2013","unstructured":"Figueroa, K., Paredes, R.: List of clustered permutations for proximity searching. In: Brisaboa, N., Pedreira, O., Zezula, P. (eds.) SISAP 2013. LNCS, vol. 8199, pp. 50\u201358. Springer, Heidelberg (2013). doi: 10.1007\/978-3-642-41062-8_6"},{"key":"20_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/3-540-59286-5_57","volume-title":"Machine Learning: ECML-95","author":"R Kohavi","year":"1995","unstructured":"Kohavi, R.: The power of decision tables. In: Lavrac, N., Wrobel, S. (eds.) ECML 1995. LNCS, vol. 912, pp. 174\u2013189. Springer, Heidelberg (1995). doi: 10.1007\/3-540-59286-5_57"},{"key":"20_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-642-32153-5_7","volume-title":"Similarity Search and Applications","author":"J Loko\u010d","year":"2012","unstructured":"Loko\u010d, J., \u010cech, P., Nov\u00e1k, J., Skopal, T.: Cut-Region: a compact building block for hierarchical metric indexing. In: Navarro, G., Pestov, V. (eds.) SISAP 2012. LNCS, vol. 7404, pp. 85\u2013100. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-32153-5_7"},{"issue":"4","key":"20_CR11","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/2590989.2590995","volume":"42","author":"F Naumann","year":"2014","unstructured":"Naumann, F.: Data profiling revisited. ACM SIGMOD Rec. 42(4), 40\u201349 (2014)","journal-title":"ACM SIGMOD Rec."},{"issue":"1","key":"20_CR12","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.jda.2008.09.014","volume":"7","author":"M Patella","year":"2009","unstructured":"Patella, M., Ciaccia, P.: Approximate similarity search: a multi-faceted problem. J. Discrete Algorithms 7(1), 36\u201348 (2009)","journal-title":"J. Discrete Algorithms"},{"key":"20_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-319-44039-2_2","volume-title":"Advances in Databases and Information Systems","author":"E Rahm","year":"2016","unstructured":"Rahm, E.: The case for holistic data integration. In: Pokorn\u00fd, J., Ivanovi\u0107, M., Thalheim, B., \u0160aloun, P. (eds.) ADBIS 2016. LNCS, vol. 9809, pp. 11\u201327. Springer, Cham (2016). doi: 10.1007\/978-3-319-44039-2_2"},{"key":"20_CR14","unstructured":"Stonebraker, M., et al.: Data curation at scale: the data tamer system. In: 6th Biennial Conference on Innovative Data Systems Research (CIDR) (2013)"},{"key":"20_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-319-10160-6_9","volume-title":"Data Warehousing and Knowledge Discovery","author":"J Varga","year":"2014","unstructured":"Varga, J., Romero, O., Pedersen, T.B., Thomsen, C.: Towards next generation BI systems: the analytical metadata challenge. In: Bellatreche, L., Mohania, M.K. (eds.) DaWaK 2014. LNCS, vol. 8646, pp. 89\u2013101. Springer, Cham (2014). doi: 10.1007\/978-3-319-10160-6_9"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68474-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,18]],"date-time":"2020-10-18T06:17:15Z","timestamp":1603001835000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-68474-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319684734","9783319684741"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68474-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}