{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T14:15:45Z","timestamp":1792332945049,"version":"4.4.0"},"reference-count":144,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,6,2]],"date-time":"2015-06-02T00:00:00Z","timestamp":1433203200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2015,8]]},"DOI":"10.1007\/s00778-015-0389-y","type":"journal-article","created":{"date-parts":[[2015,6,1]],"date-time":"2015-06-01T09:59:22Z","timestamp":1433152762000},"page":"557-581","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":230,"title":["Profiling relational data: a survey"],"prefix":"10.1007","volume":"24","author":[{"given":"Ziawasch","family":"Abedjan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukasz","family":"Golab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Naumann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,6,2]]},"reference":[{"key":"389_CR1","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Gr\u00fctze, T., Jentzsch, A., Naumann, F.: Mining and profiling RDF data with ProLOD++. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1198\u20131201 (2014). Demo","DOI":"10.1109\/ICDE.2014.6816740"},{"key":"389_CR2","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Lorey, J., Naumann, F.: Reconciling ontologies and the web of data. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 1532\u20131536 (2012)","DOI":"10.1145\/2396761.2398467"},{"key":"389_CR3","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Naumann, F.: Advancing the discovery of unique column combinations. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 1565\u20131570 (2011)","DOI":"10.1145\/2063576.2063801"},{"key":"389_CR4","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Naumann, F.: Synonym analysis for predicate expansion. In: Proceedings of the Extended Semantic Web Conference (ESWC), pp. 140\u2013154 (2013)","DOI":"10.1007\/978-3-642-38288-8_10"},{"key":"389_CR5","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Quian\u00e9-Ruiz, J.-A., Naumann, F.: Detecting unique column combinations on dynamic data. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1036\u20131047 (2014)","DOI":"10.1109\/ICDE.2014.6816721"},{"key":"389_CR6","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Schulze, P., Naumann, F.: DFD: efficient functional dependency discovery. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 949\u2013958 (2014)","DOI":"10.1145\/2661829.2661884"},{"key":"389_CR7","unstructured":"Agrawal, D., Bernstein, P., Bertino, E., Davidson, S., Dayal, U., Franklin, M., Gehrke, J., Haas, L., Halevy, A., Han, J., Jagadish, H.V., Labrinidis, A., Madden, S., Papakonstantinou, Y., Patel, J.M., Ramakrishnan, R., Ross, K., Shahabi, C., Suciu, D., Vaithyanathan, S., Widom, J.: Challenges and opportunities with Big Data. Technical report, Computing Community Consortium. http:\/\/cra.org\/ccc\/docs\/init\/bigdatawhitepaper.pdf (2012)"},{"key":"389_CR8","unstructured":"Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 487\u2013499 (1994)"},{"key":"389_CR9","doi-asserted-by":"crossref","unstructured":"Andritsos, P., Miller, R.J., Tsaparas, P.: Information-theoretic tools for mining database structure from large data sets. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 731\u2013742 (2004)","DOI":"10.1145\/1007568.1007650"},{"key":"389_CR10","doi-asserted-by":"crossref","unstructured":"Arenas, M., Daenen, J., Neven, F., Ugarte, M., Van den Bussche, J., Vansummeren, S.: Discovering XSD keys from XML data. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 61\u201372 (2013)","DOI":"10.1145\/2463676.2463705"},{"issue":"1","key":"389_CR11","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/0306-4379(87)90014-7","volume":"12","author":"MM Astrahan","year":"1987","unstructured":"Astrahan, M.M., Schkolnick, M., Kyu-Young, W.: Approximating the number of unique values of an attribute without sorting. Inf. Syst. 12(1), 11\u201315 (1987)","journal-title":"Inf. Syst."},{"key":"389_CR12","doi-asserted-by":"crossref","unstructured":"Auer, S., Demter, J., Martin, M., Lehmann, J.: LODStats\u2014an extensible framework for high-performance dataset analytics. In: Proceedings of the International Conference on Knowledge Engineering and Knowledge Management (EKAW), pp. 353\u2013362 (2012)","DOI":"10.1007\/978-3-642-33876-2_31"},{"key":"389_CR13","doi-asserted-by":"crossref","unstructured":"Bauckmann, J., Abedjan, Z., M\u00fcller, H., Leser, U., Naumann, F.: Discovering conditional inclusion dependencies. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 2094\u20132098 (2012)","DOI":"10.1145\/2396761.2398580"},{"key":"389_CR14","doi-asserted-by":"crossref","unstructured":"Bauckmann, J., Leser, U., Naumann, F., Tietz, V.: Efficiently detecting inclusion dependencies. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1448\u20131450 (2007)","DOI":"10.1109\/ICDE.2007.369032"},{"issue":"4","key":"389_CR15","first-page":"551","volume":"78","author":"F Benford","year":"1938","unstructured":"Benford, F.: The law of anomalous numbers. Proc. Am. Philos. Soc. 78(4), 551\u2013572 (1938)","journal-title":"Proc. Am. Philos. Soc."},{"key":"389_CR16","doi-asserted-by":"crossref","unstructured":"Berti-Equille, L., Dasu, T., Srivastava, D.: Discovery of complex glitch patterns: a novel approach to quantitative data cleaning. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 733\u2013744 (2011)","DOI":"10.1109\/ICDE.2011.5767864"},{"key":"389_CR17","unstructured":"Bex, G.J., Neven, F., Vansummeren, S.: Inferring XML schema definitions from XML data. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 998\u20131009 (2007)"},{"issue":"3","key":"389_CR18","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.websem.2011.06.001","volume":"9","author":"C B\u00f6hm","year":"2011","unstructured":"B\u00f6hm, C., Lorey, J., Naumann, F.: Creating void descriptions for web-scale data. J. Web Semant. 9(3), 339\u2013345 (2011)","journal-title":"J. Web Semant."},{"key":"389_CR19","unstructured":"Bravo, L., Fan, W., Ma, S.: Extending dependencies with conditions. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 243\u2013254 (2007)"},{"issue":"4","key":"389_CR20","first-page":"543","volume":"21","author":"E Brill","year":"1995","unstructured":"Brill, E.: Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging. Comput. Linguist. 21(4), 543\u2013565 (1995)","journal-title":"Comput. Linguist."},{"issue":"2","key":"389_CR21","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1145\/253262.253327","volume":"26","author":"S Brin","year":"1997","unstructured":"Brin, S., Motwani, R., Silverstein, C.: Beyond market baskets: generalizing association rules to correlations. SIGMOD Rec. 26(2), 265\u2013276 (1997)","journal-title":"SIGMOD Rec."},{"issue":"8","key":"389_CR22","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1016\/S0306-4379(03)00028-0","volume":"28","author":"P Buneman","year":"2003","unstructured":"Buneman, P., Davidson, S.B., Fan, W., Hara, C.S., Tan, W.C.: Reasoning about keys for XML. Inf. Syst. 28(8), 1037\u20131063 (2003)","journal-title":"Inf. Syst."},{"issue":"3","key":"389_CR23","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s10115-006-0039-1","volume":"12","author":"V Chandola","year":"2007","unstructured":"Chandola, V., Kumar, V.: Summarization\u2014compressing data into an informative representation. Knowl. Inf. Syst. 12(3), 355\u2013378 (2007)","journal-title":"Knowl. Inf. Syst."},{"key":"389_CR24","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.14778\/1453856.1453980","volume":"1","author":"F Chiang","year":"2008","unstructured":"Chiang, F., Miller, R.J.: Discovering data quality rules. Proc. VLDB Endow. 1, 1166\u20131177 (2008)","journal-title":"Proc. VLDB Endow."},{"issue":"3","key":"389_CR25","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.datak.2004.09.002","volume":"53","author":"RHL Chiang","year":"2005","unstructured":"Chiang, R.H.L., Cecil, C.E.H., Lim, E.-P.: Linear correlation discovery in databases: a data mining approach. Data Knowl. Eng. 53(3), 311\u2013337 (2005)","journal-title":"Data Knowl. Eng."},{"key":"389_CR26","unstructured":"Choi, B.: What are real DTDs like? In: Proceedings of the ACM SIGMOD Workshop on the Web and Databases (WebDB), pp. 43\u201348 (2002)"},{"key":"389_CR27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching. Springer, Berlin (2012)"},{"key":"389_CR28","doi-asserted-by":"crossref","unstructured":"Chu, X., Ilyas, I., Papotti, P., Ye, Y.: RuleMiner: data quality rules discovery. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1222\u20131225 (2014)","DOI":"10.1109\/ICDE.2014.6816746"},{"issue":"13","key":"389_CR29","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.14778\/2536258.2536262","volume":"6","author":"X Chu","year":"2013","unstructured":"Chu, X., Ilyas, I.F., Papotti, P.: Discovering denial constraints. Proc. VLDB Endow. 6(13), 1498\u20131509 (2013)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR30","unstructured":"Cong, G., Fan, W., Geerts, F., Jia, X., Ma, S.: Improving data quality: consistency and accuracy. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 315\u2013326 (2007)"},{"issue":"13","key":"389_CR31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/1900000004","volume":"4","author":"G Cormode","year":"2011","unstructured":"Cormode, G., Garofalakis, M., Haas, P.J., Jermaine, C.: Synopses for massive data: samples, histograms, wavelets, sketches. Found. Trends Databases 4(13), 1\u2013294 (2011)","journal-title":"Found. Trends Databases"},{"key":"389_CR32","doi-asserted-by":"crossref","unstructured":"Cormode, G., Golab, L., Flip, K., McGregor, A., Srivastava, D., Zhang, X.: Estimating the confidence of conditional functional dependencies. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 469\u2013482 (2009)","DOI":"10.1145\/1559845.1559895"},{"key":"389_CR33","doi-asserted-by":"crossref","unstructured":"Cormode, G., Korn, F., Muthukrishnan, S., Srivastava, D.: Space- and time-efficient deterministic algorithms for biased quantiles over data streams. In: Proceedings of the Symposium on Principles of Database Systems (PODS), pp. 263\u2013272 (2006)","DOI":"10.1145\/1142351.1142389"},{"key":"389_CR34","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., Ebaid, A., Eldawy, A., Elmagarmid, A., Ilyas, I.F., Ouzzani, M., Tang, N.: NADEEF: a commodity data cleaning system. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 541\u2013552 (2013)","DOI":"10.1145\/2463676.2465327"},{"key":"389_CR35","doi-asserted-by":"crossref","unstructured":"Das, A., Ng, W.-K., Woon, Y.-K.: Rapid association rule mining. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 474\u2013481 (2001)","DOI":"10.1145\/502585.502665"},{"key":"389_CR36","unstructured":"Dasu, T., Johnson, T.: Hunting of the snark: finding data glitches using data mining methods. In: Proceedings of the International Conference on Information Quality (IQ), pp. 89\u201398 (1999)"},{"issue":"2","key":"389_CR37","first-page":"43","volume":"29","author":"T Dasu","year":"2006","unstructured":"Dasu, T., Johnson, T., Marathe, A.: Database exploration using database dynamics. IEEE Data Eng. Bull. 29(2), 43\u201359 (2006)","journal-title":"IEEE Data Eng. Bull."},{"key":"389_CR38","doi-asserted-by":"crossref","unstructured":"Dasu, T., Johnson, T., Muthukrishnan, S., Shkapenyuk, V.: Mining database structure; or, how to build a data quality browser. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 240\u2013251 (2002)","DOI":"10.1145\/564691.564719"},{"issue":"11","key":"389_CR39","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.14778\/2350229.2350279","volume":"5","author":"T Dasu","year":"2012","unstructured":"Dasu, T., Loh, J.M.: Statistical distortion: consequences of data cleaning. Proc. VLDB Endow. 5(11), 1674\u20131683 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR40","doi-asserted-by":"crossref","unstructured":"Dasu, T., Loh, J.M., Srivastava, D.: Empirical glitch explanations. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 572\u2013581 (2014)","DOI":"10.1145\/2623330.2623716"},{"key":"389_CR41","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Garofalakis, M., Rastogi, R.: Independence is good: dependency-based histogram synopses for high-dimensional data. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 199\u2013210 (2001)","DOI":"10.1145\/375663.375685"},{"issue":"3","key":"389_CR42","first-page":"205","volume":"4","author":"T Diallo","year":"2012","unstructured":"Diallo, T., Novelli, N., Petit, J.-M.: Discovering (frequent) constant conditional functional dependencies. Int. J. Data Min. Model. Manag. 4(3), 205\u2013223 (2012)","journal-title":"Int. J. Data Min. Model. Manag."},{"key":"389_CR43","unstructured":"Ester, M., Kriegel, H.-P., Sander, J., Wimmer, M., Xu, X.: Incremental clustering for mining in a data warehousing environment. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 323\u2013333 (1998)"},{"key":"389_CR44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-38721-0","volume-title":"Ontology Matching","author":"J Euzenat","year":"2013","unstructured":"Euzenat, J., Shvaiko, P.: Ontology Matching, 2nd edn. Springer, Berlin (2013)","edition":"2"},{"issue":"2","key":"389_CR45","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.14778\/1454159.1454200","volume":"1","author":"W Fan","year":"2008","unstructured":"Fan, W., Geerts, F., Jia, X.: Semandaq: a data quality system based on conditional functional dependencies. Proc. VLDB Endow. 1(2), 1460\u20131463 (2008)","journal-title":"Proc. VLDB Endow."},{"issue":"2","key":"389_CR46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1366102.1366103","volume":"33","author":"W Fan","year":"2008","unstructured":"Fan, W., Geerts, F., Jia, X., Kementsietsidis, A.: Conditional functional dependencies for capturing data inconsistencies. ACM Trans. Database Syst. 33(2), 1\u201348 (2008)","journal-title":"ACM Trans. Database Syst."},{"issue":"4","key":"389_CR47","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1109\/TKDE.2010.154","volume":"23","author":"W Fan","year":"2011","unstructured":"Fan, W., Geerts, F., Li, J., Xiong, M.: Discovering conditional functional dependencies. IEEE Trans. Knowl. Data Eng. 23(4), 683\u2013698 (2011)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"389_CR48","doi-asserted-by":"crossref","unstructured":"Fan, W., Geerts, F., Ma, S., M\u00fcller, H.: Detecting inconsistencies in distributed data. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 64\u201375 (2010)","DOI":"10.1109\/ICDE.2010.5447855"},{"issue":"1","key":"389_CR49","doi-asserted-by":"crossref","first-page":"407","DOI":"10.14778\/1687627.1687674","volume":"2","author":"W Fan","year":"2009","unstructured":"Fan, W., Jia, X., Li, J., Ma, S.: Reasoning about record matching rules. Proc. VLDB Endow. 2(1), 407\u2013418 (2009)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR50","doi-asserted-by":"crossref","unstructured":"Fan, W., Li, J., Tang, N., Yu, W.: Incremental detection of inconsistencies in distributed data. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 318\u2013329 (2012)","DOI":"10.1109\/ICDE.2012.82"},{"issue":"4","key":"389_CR51","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/j.ic.2008.12.008","volume":"207","author":"H Fernau","year":"2009","unstructured":"Fernau, H.: Algorithms for learning regular expressions from positive data. Inf. Comput. 207(4), 521\u2013541 (2009)","journal-title":"Inf. Comput."},{"issue":"3","key":"389_CR52","first-page":"139","volume":"12","author":"PA Flach","year":"1999","unstructured":"Flach, P.A., Savnik, I.: Database dependency discovery: a machine learning approach. AI Commun. 12(3), 139\u2013160 (1999)","journal-title":"AI Commun."},{"issue":"3","key":"389_CR53","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.tcs.2007.02.031","volume":"378","author":"S Ganguly","year":"2007","unstructured":"Ganguly, S.: Counting distinct items over update streams. Theor. Comput. Sci. 378(3), 211\u2013222 (2007)","journal-title":"Theor. Comput. Sci."},{"issue":"10","key":"389_CR54","doi-asserted-by":"crossref","first-page":"937","DOI":"10.14778\/2536206.2536220","volume":"6","author":"M Garofalakis","year":"2013","unstructured":"Garofalakis, M., Keren, D., Samoladas, V.: Sketch-based geometric monitoring of distributed stream queries. Proc. VLDB Endow. 6(10), 937\u2013948 (2013)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR55","unstructured":"Giannella, C., Wyss, C.: Finding minimal keys in a relation instance (1999). http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=?doi=10.1.1.41.7086"},{"key":"389_CR56","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/0304-3975(83)90084-1","volume":"26","author":"S Ginsburg","year":"1983","unstructured":"Ginsburg, S., Hull, R.: Order dependency in the relational model. Theor. Comput. Sci. 26, 149\u2013195 (1983)","journal-title":"Theor. Comput. Sci."},{"issue":"1","key":"389_CR57","doi-asserted-by":"crossref","first-page":"574","DOI":"10.14778\/1687627.1687693","volume":"2","author":"L Golab","year":"2009","unstructured":"Golab, L., Karloff, H., Korn, F., Saha, A., Srivastava, D.: Sequential dependencies. Proc. VLDB Endow. 2(1), 574\u2013585 (2009)","journal-title":"Proc. VLDB Endow."},{"issue":"1\u20132","key":"389_CR58","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.14778\/1920841.1921060","volume":"3","author":"L Golab","year":"2010","unstructured":"Golab, L., Karloff, H., Korn, F., Srivastava, D.: Data auditor: exploring data quality and semantics using pattern tableaux. Proc. VLDB Endow. 3(1\u20132), 1641\u20131644 (2010)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"389_CR59","doi-asserted-by":"crossref","first-page":"376","DOI":"10.14778\/1453856.1453900","volume":"1","author":"L Golab","year":"2008","unstructured":"Golab, L., Karloff, H., Korn, F., Srivastava, D., Bei, Y.: On generating near-optimal tableaux for conditional functional dependencies. Proc. VLDB Endow. 1(1), 376\u2013390 (2008)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR60","unstructured":"Golab, L., Korn, F., Srivastava, D.: Discovering pattern tableaux for data quality analysis: a case study. In: Proceedings of the International Workshop on Quality in Databases (QDB), pp. 47\u201353 (2011)"},{"issue":"3","key":"389_CR61","first-page":"26","volume":"34","author":"L Golab","year":"2011","unstructured":"Golab, L., Korn, F., Srivastava, D.: Efficient and effective analysis of data quality using pattern tableaux. IEEE Data Eng. Bull. 34(3), 26\u201333 (2011)","journal-title":"IEEE Data Eng. Bull."},{"key":"389_CR62","doi-asserted-by":"crossref","unstructured":"Grahne, G., Zhu, J.: Discovering approximate keys in XML data. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 453\u2013460 (2002)","DOI":"10.1145\/584792.584867"},{"issue":"1","key":"389_CR63","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1023\/A:1009726021843","volume":"1","author":"J Gray","year":"1997","unstructured":"Gray, J., Chaudhuri, S., Bosworth, A., Layman, A., Reichart, D., Venkatrao, M., Pellow, F., Pirahesh, H.: Data cube: a relational aggregation operator generalizing group-by, cross-tab, and sub totals. Data Min. Knowl. Discov. 1(1), 29\u201353 (1997)","journal-title":"Data Min. Knowl. Discov."},{"key":"389_CR64","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1145\/777943.777945","volume":"28","author":"D Gunopulos","year":"2003","unstructured":"Gunopulos, D., Khardon, R., Mannila, H., Sharma, R.S.: Discovering all most specific sentences. ACM Trans. Database Syst. 28, 140\u2013174 (2003)","journal-title":"ACM Trans. Database Syst."},{"key":"389_CR65","unstructured":"Haas, P.J., Naughton, J.F., Seshadri, S., Stokes, L.: Sampling-based estimation of the number of distinct values of an attribute. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 311\u2013322 (1995)"},{"key":"389_CR66","doi-asserted-by":"crossref","unstructured":"Hainaut, J.-L., Henrard, J., Englebert, V., Roland, D., Hick, J.-M.: Database reverse engineering. In: Liu, L., Tamer \u00d6zsu, M. (eds.) Encyclopedia of Database Systems, pp. 723\u2013728. Springer, Heidelberg (2009)","DOI":"10.4018\/978-1-60566-242-8.ch021"},{"issue":"2","key":"389_CR67","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/335191.335372","volume":"29","author":"J Han","year":"2000","unstructured":"Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. SIGMOD Rec. 29(2), 1\u201312 (2000)","journal-title":"SIGMOD Rec."},{"key":"389_CR68","doi-asserted-by":"crossref","unstructured":"Hanrahan, P.: Analytic database technology for a new kind of user\u2014the data enthusiast (keynote). In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 577\u2013578 (2012)","DOI":"10.1145\/2213836.2213902"},{"key":"389_CR69","doi-asserted-by":"crossref","unstructured":"Hegewald, J., Naumann, F., Weis, M.: XStruct: efficient schema extraction from multiple and large XML databases. In: Proceedings of the International Workshop on Database Interoperability (InterDB) (2006)","DOI":"10.1109\/ICDEW.2006.166"},{"issue":"4","key":"389_CR70","doi-asserted-by":"crossref","first-page":"301","DOI":"10.14778\/2732240.2732248","volume":"7","author":"A Heise","year":"2013","unstructured":"Heise, A., Quian\u00e9-Ruiz, J.-A., Abedjan, Z., Jentzsch, A., Naumann, F.: Scalable discovery of unique column combinations. Proc. VLDB Endow. 7(4), 301\u2013312 (2013)","journal-title":"Proc. VLDB Endow."},{"issue":"12","key":"389_CR71","doi-asserted-by":"crossref","first-page":"1700","DOI":"10.14778\/2367502.2367510","volume":"5","author":"JM Hellerstein","year":"2012","unstructured":"Hellerstein, J.M., R\u00e9, C., Schoppmann, F., Wang, D.Z., Fratkin, E., Gorajek, A., Ng, K.S., Welton, C., Feng, X., Li, K., Kumar, A.: The MADlib analytics library or MAD skills, the SQL. Proc. VLDB Endow. 5(12), 1700\u20131711 (2012)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"389_CR72","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/360402.360421","volume":"2","author":"J Hipp","year":"2000","unstructured":"Hipp, J., G\u00fcntzer, U., Nakhaeizadeh, G.: Algorithms for association rule mining\u2014a general survey and comparison. SIGKDD Explor. 2(1), 58\u201364 (2000)","journal-title":"SIGKDD Explor."},{"key":"389_CR73","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/BF01830689","volume":"28","author":"DI Holmes","year":"1994","unstructured":"Holmes, D.I.: Authorship attribution. Comput. Humanit. 28, 87\u2013106 (1994)","journal-title":"Comput. Humanit."},{"key":"389_CR74","doi-asserted-by":"crossref","unstructured":"Hua, M., Pei, J.: Cleaning disguised missing data: a heuristic approach. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 950\u2013958 (2007)","DOI":"10.1145\/1281192.1281294"},{"issue":"2","key":"389_CR75","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1093\/comjnl\/42.2.100","volume":"42","author":"Y Huhtala","year":"1999","unstructured":"Huhtala, Y., K\u00e4rkk\u00e4inen, J., Porkka, P., Toivonen, H.: TANE: an efficient algorithm for discovering functional and approximate dependencies. Comput. J. 42(2), 100\u2013111 (1999)","journal-title":"Comput. J."},{"key":"389_CR76","doi-asserted-by":"crossref","unstructured":"Ilyas, I.F., Markl, V., Haas, P.J., Brown, P., Aboulnaga, A.: CORDS: automatic discovery of correlations and soft functional dependencies. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 647\u2013658 (2004)","DOI":"10.1145\/1007568.1007641"},{"key":"389_CR77","doi-asserted-by":"crossref","unstructured":"Ioannidis, Y.: The history of histograms (abridged). In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 19\u201330 (2003)","DOI":"10.1016\/B978-012722442-8\/50011-2"},{"issue":"3","key":"389_CR78","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain, A.K., Narasimha Murty, M., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264\u2013323 (1999)","journal-title":"ACM Comput. Surv."},{"key":"389_CR79","volume-title":"Encyclopedia of Database Systems, chapter Data Profiling","author":"T Johnson","year":"2009","unstructured":"Johnson, T.: Encyclopedia of Database Systems, chapter Data Profiling. Springer, Heidelberg (2009)"},{"key":"389_CR80","unstructured":"Kache, H., Han, W.-S., Markl, V., Raman, V., Ewen, S.: POP\/FED: progressive query optimization for federated queries in DB2. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 1175\u20131178 (2006)"},{"key":"389_CR81","doi-asserted-by":"crossref","unstructured":"Kandel, S., Parikh, R., Paepcke, A., Hellerstein, J., Heer, J.: Profiler: integrated statistical analysis and visualization for data quality assessment. In: Proceedings of Advanced Visual Interfaces (AVI), pp. 547\u2013554 (2012)","DOI":"10.1145\/2254556.2254659"},{"key":"389_CR82","doi-asserted-by":"crossref","unstructured":"Kang, J., Naughton, J.F.: On schema matching with opaque column names and data values. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 205\u2013216 (2003)","DOI":"10.1145\/872757.872783"},{"key":"389_CR83","doi-asserted-by":"crossref","unstructured":"Keim, D.A., Oelke, D.: Literature fingerprinting: a new method for visual literary analysis. In: Proceedings of Visual Analytics Science and Technology (VAST), pp. 115\u2013122 (2007)","DOI":"10.1109\/VAST.2007.4389004"},{"key":"389_CR84","doi-asserted-by":"crossref","unstructured":"Khoussainova, N., Balazinska, M., Suciu, D.: Towards correcting input data errors probabilistically using integrity constraints. In: Proceedings of the ACM International Workshop on Data Engineering for Wireless and Mobile Access (MobiDE), pp. 43\u201350 (2006)","DOI":"10.1145\/1140104.1140114"},{"key":"389_CR85","doi-asserted-by":"crossref","unstructured":"Kivinen, J., Mannila, H.: Approximate inference of functional dependencies from relations. In: Proceedings of the International Conference on Database Theory (ICDT), pp. 129\u2013149 (1995)","DOI":"10.1016\/0304-3975(95)00028-U"},{"key":"389_CR86","doi-asserted-by":"crossref","unstructured":"Koehler, H., Leck, U., Link, S., Prade, H.: Logical foundations of possibilistic keys. In: Ferm\u00e9, E., Leite, J. (eds.) Logics in Artificial Intelligence, volume 8761 of Lecture Notes in Computer Science, pp. 181\u2013195. Springer, Heidelberg (2014)","DOI":"10.1007\/978-3-319-11558-0_13"},{"key":"389_CR87","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/11617808_7","volume":"3870","author":"A Koeller","year":"2006","unstructured":"Koeller, A., Rundensteiner, E.A.: Heuristic strategies for the discovery of inclusion dependencies and other patterns. J. Data Semant. V. 3870, 185\u2013210 (2006)","journal-title":"J. Data Semant. V."},{"issue":"9","key":"389_CR88","doi-asserted-by":"crossref","first-page":"601","DOI":"10.14778\/2536360.2536361","volume":"6","author":"F Korn","year":"2013","unstructured":"Korn, F., Saha, B., Srivastava, D., Ying, S.: On repairing structural problems in semi-structured data. Proc. VLDB Endow. 6(9), 601\u2013612 (2013)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR89","doi-asserted-by":"crossref","unstructured":"Koudas, N., Saha, A., Srivastava, D., Venkatasubramanian, S.: Metric functional dependencies. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1275\u20131278 (2009)","DOI":"10.1109\/ICDE.2009.219"},{"key":"389_CR90","unstructured":"Laney, D.: 3D data management: controlling data volume, velocity and variety. Technical report, Gartner (2001)"},{"issue":"3","key":"389_CR91","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1093\/comjnl\/bxs082","volume":"56","author":"J Li","year":"2013","unstructured":"Li, J., Liu, J., Toivonen, H., Yong, J.: Effective pruning for the discovery of conditional functional dependencies. Comput. J. 56(3), 378\u2013392 (2013)","journal-title":"Comput. J."},{"key":"389_CR92","doi-asserted-by":"crossref","unstructured":"Li, Y., Krishnamurthy, R., Raghavan, S., Vaithyanathan, S., Jagadish, H.V.: Regular expression learning for information extraction. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 21\u201330 (2008)","DOI":"10.3115\/1613715.1613719"},{"key":"389_CR93","unstructured":"Liu, B.: Sentiment analysis and subjectivity. Handbook of Natural Language Processing, 2nd edn. Chapman and Hall\/CRC, London (2010)"},{"issue":"2","key":"389_CR94","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/TKDE.2010.197","volume":"24","author":"J Liu","year":"2012","unstructured":"Liu, J., Li, J., Liu, C., Chen, Y.: Discover dependencies from data\u2014a review. IEEE Trans. Knowl. Data Eng. 24(2), 251\u2013264 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"389_CR95","doi-asserted-by":"crossref","unstructured":"Lopes, S., Petit, J.-M., Lakhal, L.: Efficient discovery of functional dependencies and Armstrong relations. In: Proceedings of the International Conference on Extending Database Technology (EDBT), pp. 350\u2013364 (2000)","DOI":"10.1007\/3-540-46439-5_24"},{"issue":"1","key":"389_CR96","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0306-4379(01)00027-8","volume":"27","author":"S Lopes","year":"2002","unstructured":"Lopes, S., Petit, J.-M., Toumani, F.: Discovering interesting inclusion dependencies: application to logical database tuning. Inf. Syst. 27(1), 1\u201319 (2002)","journal-title":"Inf. Syst."},{"issue":"2","key":"389_CR97","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/0022-0000(78)90009-0","volume":"17","author":"CL Lucchesi","year":"1978","unstructured":"Lucchesi, C.L., Osborn, S.L.: Candidate keys for relations. J. Comput. Syst. Sci. 17(2), 270\u2013279 (1978)","journal-title":"J. Comput. Syst. Sci."},{"key":"389_CR98","unstructured":"Madhavan, J., Bernstein, P.A., Rahm, E.: Generic schema matching with Cupid. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 49\u201358 (2001)"},{"issue":"3","key":"389_CR99","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1145\/62061.62063","volume":"20","author":"MV Mannino","year":"1988","unstructured":"Mannino, M.V., Chu, P., Sager, T.: Statistical profile estimation in database systems. ACM Comput. Surv. 20(3), 191\u2013221 (1988)","journal-title":"ACM Comput. Surv."},{"key":"389_CR100","doi-asserted-by":"crossref","unstructured":"De Marchi, F., Lopes, S., Petit, J.-M.: Efficient algorithms for mining inclusion dependencies. In: Proceedings of the International Conference on Extending Database Technology (EDBT), pp. 464\u2013476 (2002)","DOI":"10.1007\/3-540-45876-X_30"},{"key":"389_CR101","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s10844-007-0048-x","volume":"32","author":"F Marchi De","year":"2009","unstructured":"De Marchi, F., Lopes, S., Petit, J.-M.: Unary and n-ary inclusion dependency discovery in relational databases. J. Intell. Inf. Syst. 32, 53\u201373 (2009)","journal-title":"J. Intell. Inf. Syst."},{"key":"389_CR102","doi-asserted-by":"crossref","unstructured":"De Marchi, F. , Petit, J.-M.: Zigzag: a new algorithm for mining large inclusion dependencies in databases. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp. 27\u201334 (2003)","DOI":"10.1109\/ICDM.2003.1250899"},{"issue":"8","key":"389_CR103","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1109\/32.57618","volume":"16","author":"VM Markowitz","year":"1990","unstructured":"Markowitz, V.M., Makowsky, J.A.: Identifying extended entity-relationship object structures in relational schemas. IEEE Trans. Softw. Eng. 16(8), 777\u2013790 (1990)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"389_CR104","volume-title":"Data Quality Assessment","author":"A Maydanchik","year":"2007","unstructured":"Maydanchik, A.: Data Quality Assessment. Technics Publications, New Jersey (2007)"},{"key":"389_CR105","doi-asserted-by":"crossref","unstructured":"Mignet, L., Barbosa, D., Veltri, P.: The XML web: a first study. In: Proceedings of the International World Wide Web Conference (WWW), pp. 500\u2013510 (2003)","DOI":"10.1145\/775152.775223"},{"key":"389_CR106","unstructured":"Mlynkova, I., Toman, K., Pokorn\u00fd, J.: Statistical analysis of real XML data collections. In: Proceedings of the International Conference on Management of Data (COMAD), pp. 15\u201326 (2006)"},{"issue":"6","key":"389_CR107","doi-asserted-by":"crossref","first-page":"453","DOI":"10.14778\/2732279.2732282","volume":"7","author":"K Morton","year":"2014","unstructured":"Morton, K., Balazinska, M., Grossman, D., Mackinlay, J.: Support the data enthusiast: challenges for next-generation data-analysis systems. Proc. VLDB Endow. 7(6), 453\u2013456 (2014)","journal-title":"Proc. VLDB Endow."},{"issue":"4","key":"389_CR108","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/2590989.2590995","volume":"42","author":"F Naumann","year":"2013","unstructured":"Naumann, F.: Data profiling revisited. SIGMOD Rec. 42(4), 40\u201349 (2013)","journal-title":"SIGMOD Rec."},{"key":"389_CR109","doi-asserted-by":"crossref","unstructured":"Naumann, F., Ho, C.-T., Tian, X., Haas, L., Megiddo, N.: Attribute classification using feature analysis. In: Proceedings of the International Conference on Data Engineering (ICDE), p 271 (2002)","DOI":"10.1109\/ICDE.2002.994725"},{"key":"389_CR110","doi-asserted-by":"crossref","unstructured":"Novelli, N., Cicchetti, R.: FUN: an efficient algorithm for mining functional and embedded dependencies. In: Proceedings of the International Conference on Database Theory (ICDT), pp. 189\u2013203 (2001)","DOI":"10.1007\/3-540-44503-X_13"},{"issue":"1","key":"389_CR111","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1482619.1482621","volume":"27","author":"N Ntarmos","year":"2009","unstructured":"Ntarmos, N., Triantafillou, P., Weikum, G.: Distributed hash sketches: scalable, efficient, and accurate cardinality estimation for distributed multisets. ACM Trans. Comput. Syst. 27(1), 1\u201353 (2009)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"1\u20132","key":"389_CR112","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/1500000011","volume":"2","author":"B Pang","year":"2008","unstructured":"Pang, B., Lee, L.: Opinion mining and sentiment analysis. Found. Trends Inf. Retr. 2(1\u20132), 1\u2013135 (2008)","journal-title":"Found. Trends Inf. Retr."},{"key":"389_CR113","doi-asserted-by":"crossref","unstructured":"Papenbrock, T., Ehrlich, J., Marten, J., Neubert, T., Rudolph, J.-P., Sch\u00f6nberg, M., Zwiener, J., Naumann, F.: Functional dependency discovery: an experimental evaluation of seven algorithms. Proc. VLDB Endow. 8(10) (2015)","DOI":"10.14778\/2794367.2794377"},{"issue":"7","key":"389_CR114","doi-asserted-by":"crossref","first-page":"774","DOI":"10.14778\/2752939.2752946","volume":"8","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock, T., Kruse, S., Quian\u00e9-Ruiz, J.-A., Naumann, F.: Divide & conquer-based inclusion dependency discovery. Proc. VLDB Endow. 8(7), 774\u2013785 (2015)","journal-title":"Proc. VLDB Endow."},{"key":"389_CR115","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1109\/69.634757","volume":"9","author":"JS Park","year":"1997","unstructured":"Park, J.S., Chen, M.-S., Yu, P.S.: Using a hash-based method with transaction trimming for mining association rules. IEEE Trans. Knowl. Data Eng. 9, 813\u2013825 (1997)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"389_CR116","doi-asserted-by":"crossref","unstructured":"Petit, J.-M., Kouloumdjian, J., Boulicaut, J.-F., Toumani, F.: Using queries to improve database reverse engineering. In: Proceedings of the International Conference on Conceptual Modeling (ER), pp. 369\u2013386 (1994)","DOI":"10.1007\/3-540-58786-1_91"},{"key":"389_CR117","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1145\/505248.506010","volume":"4","author":"L Pipino","year":"2002","unstructured":"Pipino, L., Lee, Y., Wang, R.: Data quality assessment. Commun. ACM 4, 211\u2013218 (2002)","journal-title":"Commun. ACM"},{"key":"389_CR118","doi-asserted-by":"crossref","unstructured":"Poosala, V., Haas, P.J., Ioannidis, Y.E., Shekita, E.J.: Improved histograms for selectivity estimation of range predicates. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 294\u2013305 (1996)","DOI":"10.1145\/233269.233342"},{"key":"389_CR119","unstructured":"Poosala, V., Ioannidis, Y.E.: Selectivity estimation without the attribute value independence assumption. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 486\u2013495 (1997)"},{"key":"389_CR120","volume-title":"Data Preparation for Data Mining","author":"D Pyle","year":"1999","unstructured":"Pyle, D.: Data Preparation for Data Mining. Morgan Kaufmann, Burlington (1999)"},{"issue":"4","key":"389_CR121","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.-H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"389_CR122","unstructured":"Raman, V., Hellerstein, J.M.: Potters wheel: an interactive data cleaning system. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 381\u2013390 (2001)"},{"key":"389_CR123","unstructured":"Rostin, A., Albrecht, O., Bauckmann, J., Naumann, F., Leser, U.: A machine learning approach to foreign key discovery. In: Proceedings of the ACM SIGMOD Workshop on the Web and Databases (WebDB) (2009)"},{"key":"389_CR124","unstructured":"Sahuguet, A., Azavant, F.: Building light-weight wrappers for legacy Web data-sources using W4F. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 738\u2013741 (1999)"},{"issue":"3","key":"389_CR125","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1561\/1900000003","volume":"1","author":"S Sarawagi","year":"2008","unstructured":"Sarawagi, S.: Information extraction. Found. Trends Databases 1(3), 261\u2013377 (2008)","journal-title":"Found. Trends Databases"},{"key":"389_CR126","unstructured":"Sismanis, Y., Brown, P., Haas, P.J., Reinwald, B.: GORDIAN: efficient and scalable discovery of composite keys. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 691\u2013702 (2006)"},{"key":"389_CR127","unstructured":"Smith, K.P., Morse, M., Mork, P., Li, M.H., Rosenthal, A., Allen, M.D., Seligman, L.: The role of schema matching in large enterprises. In: Proceedings of the Conference on Innovative Data Systems Research (CIDR) (2009)"},{"key":"389_CR128","doi-asserted-by":"crossref","unstructured":"Song, S., Chen, L.: Differential dependencies: reasoning and discovery. ACM Trans. Database Syst. 36(3), 16:1\u201316:41 (2011)","DOI":"10.1145\/2000824.2000826"},{"key":"389_CR129","unstructured":"Stonebraker, M., Bruckner, D., Ilyas, I.F., Beskales, G., Cherniack, M., Zdonik, S., Pagan, A., Xu, S.: Data curation at scale: the Data Tamer system. In: Proceedings of the Conference on Innovative Data Systems Research (CIDR) (2013)"},{"key":"389_CR130","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/69.553155","volume":"8","author":"M Chen","year":"1996","unstructured":"Chen, M., Hun, J., Yu, P.S.: Data mining: an overview from a database perspective. IEEE Trans. Knowl. Data Eng. 8, 866\u2013883 (1996)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"389_CR131","doi-asserted-by":"crossref","unstructured":"Tsai, P.S.M., Lee, C.-C., Chen, A.L.P.: An efficient approach for incremental association rule mining. Methodologies for Knowledge Discovery and Data Mining. volume 1574 of Lecture Notes in Computer Science, pp. 74\u201383. Springer, Heidelberg (1999)","DOI":"10.1007\/3-540-48912-6_10"},{"issue":"3","key":"389_CR132","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1145\/1016028.1016029","volume":"29","author":"MW Vincent","year":"2004","unstructured":"Vincent, M.W., Liu, J., Liu, C.: Strong functional dependencies and their application to normal forms in XML. ACM Trans. Database Syst. 29(3), 445\u2013462 (2004)","journal-title":"ACM Trans. Database Syst."},{"key":"389_CR133","doi-asserted-by":"crossref","unstructured":"Vogel, T., Naumann, F.: Instance-based \u201cone-to-some\u201d assignment of similarity measures to attributes. In: Proceedings of the International Conference on Cooperative Information Systems (CoopIS), pp. 412\u2013420 (2011)","DOI":"10.1007\/978-3-642-25109-2_27"},{"key":"389_CR134","doi-asserted-by":"crossref","unstructured":"Wang, S.-L., Tsou, W.-C., Lin, J.-H., Hong, T.-P.: Maintenance of discovered functional dependencies: incremental deletion. Intelligent Systems Design and Applications, volume 23 of Advances in Soft Computing, pp. 579\u2013588. Springer, Heidelberg (2003)","DOI":"10.1007\/978-3-540-44999-7_55"},{"issue":"3","key":"389_CR135","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/1010614.1010616","volume":"22","author":"W Xindong","year":"2004","unstructured":"Xindong, W., Zhang, C., Zhang, S.: Efficient mining of both positive and negative association rules. ACM Trans. Inf. Syst. 22(3), 381\u2013405 (2004)","journal-title":"ACM Trans. Inf. Syst."},{"key":"389_CR136","doi-asserted-by":"crossref","unstructured":"Wyss, C., Giannella, C., Robertson, E.L.: FastFDs: a heuristic-driven, depth-first algorithm for mining functional dependencies from relation instances. In: Proceedings of the International Conference on Data Warehousing and Knowledge Discovery (DaWaK), pp. 101\u2013110 (2001)","DOI":"10.1007\/3-540-44801-2_11"},{"issue":"3","key":"389_CR137","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu, R., Wunsch II, D.C.: Survey of clustering algorithms. IEEE Trans. Neural Netw. 16(3), 645\u2013678 (2005)","journal-title":"IEEE Trans. Neural Netw."},{"key":"389_CR138","doi-asserted-by":"crossref","unstructured":"Yakout, M., Elmagarmid, A.K., Neville, J., Ouzzani, M.: GDR: a system for guided data repair. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 1223\u20131226 (2010)","DOI":"10.1145\/1807167.1807325"},{"issue":"2","key":"389_CR139","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s10618-007-0083-9","volume":"16","author":"H Yao","year":"2008","unstructured":"Yao, H., Hamilton, H.J.: Mining functional dependencies from data. Data Min. Knowl. Discov. 16(2), 197\u2013219 (2008)","journal-title":"Data Min. Knowl. Discov."},{"key":"389_CR140","unstructured":"Yu, C., Jagadish, H.V.: Efficient discovery of XML data redundancies. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 103\u2013114 (2006)"},{"issue":"3","key":"389_CR141","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1109\/69.846291","volume":"12","author":"MJ Zaki","year":"2000","unstructured":"Zaki, M.J.: Scalable algorithms for association mining. IEEE Trans. Knowl. Data Eng. 12(3), 372\u2013390 (2000)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"389_CR142","doi-asserted-by":"crossref","unstructured":"Zhang, M., Chakrabarti, K.: InfoGather+: semantic matching and annotation of numeric and time-varying attributes in web tables. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 145\u2013156 (2013)","DOI":"10.1145\/2463676.2465276"},{"key":"389_CR143","doi-asserted-by":"crossref","unstructured":"Zhang, M., Hadjieleftheriou, M., Ooi, B.C., Procopiuc, C.M., Srivastava, D.: On multi-column foreign key discovery. Proc. VLDB Endow. 3(1\u20132), 805\u2013814 (2010)","DOI":"10.14778\/1920841.1920944"},{"key":"389_CR144","doi-asserted-by":"crossref","unstructured":"Zhang, M., Hadjieleftheriou, M., Ooi, B.C., Procopiuc, C.M., Srivastava, D.: Automatic discovery of attributes in relational databases. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 109\u2013120 (2011)","DOI":"10.1145\/1989323.1989336"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0389-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-015-0389-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0389-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T22:31:45Z","timestamp":1566772305000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-015-0389-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,2]]},"references-count":144,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,8]]}},"alternative-id":["389"],"URL":"https:\/\/doi.org\/10.1007\/s00778-015-0389-y","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,6,2]]}}}