{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:06:52Z","timestamp":1792598812631,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":268,"publisher":"ACM","isbn-type":[{"value":"9781450371520","type":"print"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,9]]},"DOI":"10.1145\/3310205","type":"monograph","created":{"date-parts":[[2019,7,11]],"date-time":"2019-07-11T21:09:06Z","timestamp":1562879346000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":212,"title":["Data Cleaning"],"prefix":"10.1145","author":[{"given":"Ihab F.","family":"Ilyas","sequence":"first","affiliation":[{"name":"University of Waterloo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Chu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,7,9]]},"reference":[{"key":"e_1_4_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"e_1_4_1_2_1","first-page":"1134","volume-title":"Proceedings of the 32nd International Conference on Data Engineering","author":"Abedjan Z.","unstructured":"Z. Abedjan , J. Morcos , I. F. Ilyas , M. Ouzzani , P. Papotti , and M. Stonebraker . 2016b. Dataxformer: A robust transformation discovery system . In Proceedings of the 32nd International Conference on Data Engineering , pp. 1134 -- 1145 . 91, 107, 108, 110, 111, 114 Z. Abedjan, J. Morcos, I. F. Ilyas, M. Ouzzani, P. Papotti, and M. Stonebraker. 2016b. Dataxformer: A robust transformation discovery system. In Proceedings of the 32nd International Conference on Data Engineering, pp. 1134--1145. 91, 107, 108, 110, 111, 114"},{"key":"e_1_4_1_3_1","unstructured":"S. Abiteboul R. Hull and V. Vianu. 1995. Foundations of Databases. Addison-Wesley. 121 138 139 148  S. Abiteboul R. Hull and V. Vianu. 1995. Foundations of Databases. Addison-Wesley. 121 138 139 148"},{"issue":"1","key":"e_1_4_1_4_1","first-page":"1","article-title":"Database-friendly random projections. In Proceedings of the 20th ACM SIGACT-SIGMOD-SIGART Symp. on Principles of Database Systems, pp. 274--281","volume":"10","author":"Achlioptas D.","year":"2001","unstructured":"D. Achlioptas . 2001 . Database-friendly random projections. In Proceedings of the 20th ACM SIGACT-SIGMOD-SIGART Symp. on Principles of Database Systems, pp. 274--281 . ACM. DOI : 10 . 1 . 1 .28.6652. 33 D. Achlioptas. 2001. Database-friendly random projections. In Proceedings of the 20th ACM SIGACT-SIGMOD-SIGART Symp. on Principles of Database Systems, pp. 274--281. ACM. DOI: 10.1.1.28.6652. 33","journal-title":"ACM. DOI"},{"key":"e_1_4_1_5_1","first-page":"129","volume-title":"Proceedings of the 27th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems","author":"Afrati F.","unstructured":"F. Afrati and P. G. Kolaitis . 2008. Answering aggregate queries in data exchange . In Proceedings of the 27th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems , pp. 129 -- 138 . ACM. 117 F. Afrati and P. G. Kolaitis. 2008. Answering aggregate queries in data exchange. In Proceedings of the 27th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 129--138. ACM. 117"},{"key":"e_1_4_1_6_1","first-page":"31","volume-title":"Proceedings of the 12th International Conference on Database Theory","author":"Afrati F. N.","unstructured":"F. N. Afrati and P. G. Kolaitis . 2009. Repair checking in inconsistent databases: algorithms and complexity . In Proceedings of the 12th International Conference on Database Theory , pp. 31 -- 41 . 178 F. N. Afrati and P. G. Kolaitis. 2009. Repair checking in inconsistent databases: algorithms and complexity. In Proceedings of the 12th International Conference on Database Theory, pp. 31--41. 178"},{"key":"e_1_4_1_7_1","first-page":"99","volume-title":"Proceedings of the 13th International Conference on Extending Database Technology","author":"Afrati F. N.","unstructured":"F. N. Afrati and J. D. Ullman . 2010. Optimizing joins in a map-reduce environment . In Proceedings of the 13th International Conference on Extending Database Technology , pp. 99 -- 110 . 68, 69 F. N. Afrati and J. D. Ullman. 2010. Optimizing joins in a map-reduce environment. In Proceedings of the 13th International Conference on Extending Database Technology, pp. 99--110. 68, 69"},{"key":"e_1_4_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2436823"},{"key":"e_1_4_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375668"},{"key":"e_1_4_1_10_1","first-page":"487","volume-title":"Proceedings of the 20th International Conference on Very Large Data Bases, 1215","author":"Agrawal R.","unstructured":"R. Agrawal and R. Srikant . 1994. Fast algorithms for mining association rules . In Proceedings of the 20th International Conference on Very Large Data Bases, 1215 , pp. 487 -- 499 . 42 R. Agrawal and R. Srikant. 1994. Fast algorithms for mining association rules. In Proceedings of the 20th International Conference on Very Large Data Bases, 1215, pp. 487--499. 42"},{"key":"e_1_4_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/170036.170072"},{"key":"e_1_4_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1411509.1411513"},{"key":"e_1_4_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"e_1_4_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1508857.1508864"},{"key":"e_1_4_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687686"},{"key":"e_1_4_1_16_1","first-page":"783","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Arasu A.","unstructured":"A. Arasu , M. G\u00f6tz , and R. Kaushik . 2010. On active learning of record matching packages . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 783 -- 794 . 197 A. Arasu, M. G\u00f6tz, and R. Kaushik. 2010. On active learning of record matching packages. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 783--794. 197"},{"key":"e_1_4_1_17_1","first-page":"68","volume-title":"Proceedings of the 18th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems","author":"Arenas M.","unstructured":"M. Arenas , L. Bertossi , and J. Chomicki . 1999. Consistent query answers in inconsistent databases . In Proceedings of the 18th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems , pp. 68 -- 79 . 179, 191 M. Arenas, L. Bertossi, and J. Chomicki. 1999. Consistent query answers in inconsistent databases. In Proceedings of the 18th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 68--79. 179, 191"},{"key":"e_1_4_1_18_1","doi-asserted-by":"crossref","unstructured":"M. Arenas P. Barcel\u00f3 L. Libkin and F. Murlak. 2014. Foundations of Data Exchange. Cambridge University Press. 114 117  M. Arenas P. Barcel\u00f3 L. Libkin and F. Murlak. 2014. Foundations of Data Exchange. Cambridge University Press. 114 117","DOI":"10.1017\/CBO9781139060158"},{"key":"e_1_4_1_19_1","first-page":"409","volume-title":"Proceedings of the 2007 IEEE International Conference on Data Mining","author":"Assent I.","unstructured":"I. Assent , R. Krieger , E. M\u00fcller , and T. Seidl . 2007. Dusc: Dimensionality unbiased subspace clustering . In Proceedings of the 2007 IEEE International Conference on Data Mining , pp. 409 -- 414 . IEEE. 39 I. Assent, R. Krieger, E. M\u00fcller, and T. Seidl. 2007. Dusc: Dimensionality unbiased subspace clustering. In Proceedings of the 2007 IEEE International Conference on Data Mining, pp. 409--414. IEEE. 39"},{"key":"e_1_4_1_20_1","first-page":"1093","volume-title":"Proceedings of the 17th ACM International Conference on Information and Knowledge Management","author":"Assent I.","unstructured":"I. Assent , R. Krieger , E. M\u00fcller , and T. Seidl . 2008. Edsc: efficient density-based subspace clustering . In Proceedings of the 17th ACM International Conference on Information and Knowledge Management , pp. 1093 -- 1102 . ACM. 39 I. Assent, R. Krieger, E. M\u00fcller, and T. Seidl. 2008. Edsc: efficient density-based subspace clustering. In Proceedings of the 17th ACM International Conference on Information and Knowledge Management, pp. 1093--1102. ACM. 39"},{"key":"e_1_4_1_21_1","first-page":"541","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Bailis P.","unstructured":"P. Bailis , E. Gan , S. Madden , D. Narayanan , K. Rong , and S. Suri . 2017. Macrobase: Prioritizing attention in fast data . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 541 -- 556 . 5 P. Bailis, E. Gan, S. Madden, D. Narayanan, K. Rong, and S. Suri. 2017. Macrobase: Prioritizing attention in fast data. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 541--556. 5"},{"key":"e_1_4_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1274531.1274545"},{"key":"e_1_4_1_23_1","unstructured":"V. Barnett and T. Lewis. 1994. Outliers in Statistical Data. Wiley New York. 4 11 15 19 44 195  V. Barnett and T. Lewis. 1994. Outliers in Statistical Data. Wiley New York. 4 11 15 19 44 195"},{"key":"e_1_4_1_24_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1999.1632"},{"key":"e_1_4_1_25_1","first-page":"29","volume-title":"Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Bay S. D.","unstructured":"S. D. Bay and M. Schwabacher . 2003. Mining distance-based outliers in near linear time with randomization and a simple pruning rule . In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pp. 29 -- 38 . 28 S. D. Bay and M. Schwabacher. 2003. Mining distance-based outliers in near linear time with randomization and a simple pruning rule. In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 29--38. 28"},{"key":"e_1_4_1_26_1","first-page":"131","volume-title":"Proceedings of the 16th International World Wide Web Conference","author":"Bayardo R. J.","unstructured":"R. J. Bayardo , Y. Ma , and R. Srikant . 2007. Scaling up all pairs similarity search . In Proceedings of the 16th International World Wide Web Conference , pp. 131 -- 140 . ACM. 64 R. J. Bayardo, Y. Ma, and R. Srikant. 2007. Scaling up all pairs similarity search. In Proceedings of the 16th International World Wide Web Conference, pp. 131--140. ACM. 64"},{"key":"e_1_4_1_27_1","first-page":"212","volume-title":"Proceedings of the 33rd ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems","author":"Beame P.","unstructured":"P. Beame , P. Koutris , and D. Suciu . 2014. Skew in parallel query processing . In Proceedings of the 33rd ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems , pp. 212 -- 223 . 67, 69 P. Beame, P. Koutris, and D. Suciu. 2014. Skew in parallel query processing. In Proceedings of the 33rd ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 212--223. 67, 69"},{"key":"e_1_4_1_28_1","volume-title":"Database Repairing and Consistent Query Answering","author":"Bertossi L. E.","unstructured":"L. E. Bertossi . 2011. Database Repairing and Consistent Query Answering . Morgan & Claypool Publishers . 2, 178, 179, 191 L. E. Bertossi. 2011. Database Repairing and Consistent Query Answering. Morgan & Claypool Publishers. 2, 178, 179, 191"},{"key":"e_1_4_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687695"},{"key":"e_1_4_1_30_1","volume-title":"Proceedings of the VLDB Endowment, 3(1--2): 197--207","author":"Beskales G.","unstructured":"G. Beskales , I. F. Ilyas , and L. Golab . 2010. Sampling the repairs of functional dependency violations under hard constraints . Proceedings of the VLDB Endowment, 3(1--2): 197--207 . 163, 164, 181, 191, 193 G. Beskales, I. F. Ilyas, and L. Golab. 2010. Sampling the repairs of functional dependency violations under hard constraints. Proceedings of the VLDB Endowment, 3(1--2): 197--207. 163, 164, 181, 191, 193"},{"key":"e_1_4_1_31_1","first-page":"541","volume-title":"Proceedings of the 29th International Conference on Data Engineering","author":"Beskales G.","unstructured":"G. Beskales , I. F. Ilyas , L. Golab , and A. Galiullin . 2013. On the relative trust between inconsistent data and inaccurate constraints . In Proceedings of the 29th International Conference on Data Engineering , pp. 541 -- 552 . 164, 173, 174, 176 G. Beskales, I. F. Ilyas, L. Golab, and A. Galiullin. 2013. On the relative trust between inconsistent data and inaccurate constraints. In Proceedings of the 29th International Conference on Data Engineering, pp. 541--552. 164, 173, 174, 176"},{"key":"e_1_4_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-013-0316-z"},{"key":"e_1_4_1_33_1","volume-title":"i. F. Ilyas, and L. Golab","author":"Beskales G.","year":"2010","unstructured":"G. Beskales , i. F. Ilyas, and L. Golab . 2010 . Sampling the repairs of functional dependency violations under hard constraints. Proceedings VLDB Endowment , 3(1--2): 197--207. G. Beskales, i. F. Ilyas, and L. Golab. 2010. Sampling the repairs of functional dependency violations under hard constraints. Proceedings VLDB Endowment, 3(1--2): 197--207."},{"key":"e_1_4_1_34_1","first-page":"217","volume-title":"Proceedings of the 7th International Conference on Database Theory","author":"Beyer K.","unstructured":"K. Beyer , J. Goldstein , R. Ramakrishnan , and U. Shaft . 1999. When is \"nearest neighbor\" meaningful ? In Proceedings of the 7th International Conference on Database Theory , pp. 217 -- 235 . Springer. 12, 32 K. Beyer, J. Goldstein, R. Ramakrishnan, and U. Shaft. 1999. When is \"nearest neighbor\" meaningful? In Proceedings of the 7th International Conference on Database Theory, pp. 217--235. Springer. 12, 32"},{"key":"e_1_4_1_35_1","first-page":"39","volume-title":"Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Bilenko M.","unstructured":"M. Bilenko and R. J. Mooney . 2003. Adaptive duplicate detection using learnable string similarity measures . In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pp. 39 -- 48 . ACM. 55 M. Bilenko and R. J. Mooney. 2003. Adaptive duplicate detection using learnable string similarity measures. In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 39--48. ACM. 55"},{"key":"e_1_4_1_36_1","first-page":"87","volume-title":"Proceedings of the 2006 IEEE International Conference on Data Mining","author":"Bilenko M.","unstructured":"M. Bilenko , B. Kamath , and R. J. Mooney . 2006. Adaptive blocking: Learning to scale up record linkage . In Proceedings of the 2006 IEEE International Conference on Data Mining , pp. 87 -- 96 . 66 M. Bilenko, B. Kamath, and R. J. Mooney. 2006. Adaptive blocking: Learning to scale up record linkage. In Proceedings of the 2006 IEEE International Conference on Data Mining, pp. 87--96. 66"},{"key":"e_1_4_1_37_1","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop C. M.","unstructured":"C. M. Bishop . 2006. Pattern Recognition and Machine Learning (Information Science and Statistics) . Springer-Verlag . 136 C. M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag. 136"},{"key":"e_1_4_1_38_1","first-page":"245","volume-title":"SWYN: A Visual representation for regular expressions","author":"Blackwell A. F.","year":"2001","unstructured":"A. F. Blackwell . 2001 . SWYN: A Visual representation for regular expressions . In H. Lieberman, editor, Your Wish is My Command, pp. 245 -- 270 . Morgan Kaufmann Publishers Inc . 102 A. F. Blackwell. 2001. SWYN: A Visual representation for regular expressions. In H. Lieberman, editor, Your Wish is My Command, pp. 245--270. Morgan Kaufmann Publishers Inc. 102"},{"key":"e_1_4_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157800"},{"key":"e_1_4_1_40_1","doi-asserted-by":"crossref","unstructured":"J. Bleiholder and F. Naumann. 2008. Data fusion. ACM Computing Surveys 41(1). 74 75  J. Bleiholder and F. Naumann. 2008. Data fusion. ACM Computing Surveys 41(1). 74 75","DOI":"10.1145\/1456650.1456651"},{"key":"e_1_4_1_41_1","first-page":"143","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Bohannon P.","unstructured":"P. Bohannon , W. Fan , M. Flaster , and R. Rastogi . 2005. A cost-based model and effective heuristic for repairing constraints by value modification . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 143 -- 154 . ACM. 139, 163, 164, 175, 178, 179, 183, 184, 206 P. Bohannon, W. Fan, M. Flaster, and R. Rastogi. 2005. A cost-based model and effective heuristic for repairing constraints by value modification. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 143--154. ACM. 139, 163, 164, 175, 178, 179, 183, 184, 206"},{"key":"e_1_4_1_42_1","first-page":"746","volume-title":"Proceedings of the 23rd International Conference on Data Engineering","author":"Bohannon P.","unstructured":"P. Bohannon , W. Fan , F. Geerts , X. Jia , and A. Kementsietsidis . 2007. Conditional functional dependencies for data cleaning . In Proceedings of the 23rd International Conference on Data Engineering , pp. 746 -- 755 . 130 P. Bohannon, W. Fan, F. Geerts, X. Jia, and A. Kementsietsidis. 2007. Conditional functional dependencies for data cleaning. In Proceedings of the 23rd International Conference on Data Engineering, pp. 746--755. 130"},{"key":"e_1_4_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"issue":"1","key":"e_1_4_1_44_1","first-page":"1","article-title":"On the resemblance and containment of documents. In Proceedings of the Compression and Complexity of Sequences, pp. 21--29","volume":"10","author":"Broder A. Z.","year":"1997","unstructured":"A. Z. Broder . 1997 . On the resemblance and containment of documents. In Proceedings of the Compression and Complexity of Sequences, pp. 21--29 . IEEE. DOI : 10 . 1 . 1 .24.779. 62 A. Z. Broder. 1997. On the resemblance and containment of documents. In Proceedings of the Compression and Complexity of Sequences, pp. 21--29. IEEE. DOI: 10.1.1.24.779. 62","journal-title":"IEEE. DOI"},{"key":"e_1_4_1_45_1","first-page":"445","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Chalamalla A.","unstructured":"A. Chalamalla , I. F. Ilyas , M. Ouzzani , and P. Papotti . 2014. Descriptive and prescriptive data cleaning . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 445 -- 456 . 151, 153, 157, 158, 159 A. Chalamalla, I. F. Ilyas, M. Ouzzani, and P. Papotti. 2014. Descriptive and prescriptive data cleaning. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 445--456. 151, 153, 157, 158, 159"},{"key":"e_1_4_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_4_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_4_1_48_1","first-page":"865","volume-title":"Proceedings of the 21st International Conference on Data Engineering","author":"Chaudhuri S.","unstructured":"S. Chaudhuri , V. Ganti , and R. Motwani . 2005. Robust identification of fuzzy duplicates . In Proceedings of the 21st International Conference on Data Engineering , pp. 865 -- 876 . 55 S. Chaudhuri, V. Ganti, and R. Motwani. 2005. Robust identification of fuzzy duplicates. In Proceedings of the 21st International Conference on Data Engineering, pp. 865--876. 55"},{"key":"e_1_4_1_49_1","first-page":"5","volume-title":"Proceedings of the 22nd International Conference on Data Engineering","author":"Chaudhuri S.","unstructured":"S. Chaudhuri , V. Ganti , and R. Kaushik . 2006. A primitive operator for similarity joins in data cleaning . In Proceedings of the 22nd International Conference on Data Engineering , pp. 5 -- 16 . IEEE. 64 S. Chaudhuri, V. Ganti, and R. Kaushik. 2006. A primitive operator for similarity joins in data cleaning. In Proceedings of the 22nd International Conference on Data Engineering, pp. 5--16. IEEE. 64"},{"key":"e_1_4_1_50_1","first-page":"327","volume-title":"Proceedings of the 33rd International Conference on Very Large Data Bases","author":"Chaudhuri S.","unstructured":"S. Chaudhuri , B.-C. Chen , V. Ganti , and R. Kaushik . 2007. Example-driven design of efficient record matching queries . In Proceedings of the 33rd International Conference on Very Large Data Bases , pp. 327 -- 338 . 55 S. Chaudhuri, B.-C. Chen, V. Ganti, and R. Kaushik. 2007. Example-driven design of efficient record matching queries. In Proceedings of the 33rd International Conference on Very Large Data Bases, pp. 327--338. 55"},{"key":"e_1_4_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453980"},{"key":"e_1_4_1_52_1","first-page":"446","volume-title":"Proceedings of the 27th International Conference on Data Engineering","author":"Chiang F.","unstructured":"F. Chiang and R.J. Miller . 2011. A unified model for data and constraint repair . In Proceedings of the 27th International Conference on Data Engineering , pp. 446 -- 457 . 164, 173, 174, 176 F. Chiang and R.J. Miller. 2011. A unified model for data and constraint repair. In Proceedings of the 27th International Conference on Data Engineering, pp. 446--457. 164, 173, 174, 176"},{"key":"e_1_4_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/1709465.1709573"},{"key":"e_1_4_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402020"},{"key":"e_1_4_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.127"},{"key":"e_1_4_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"e_1_4_1_57_1","first-page":"458","volume-title":"Proceedings of the 29th International Conference on Data Engineering","author":"Chu X.","unstructured":"X. Chu , I. F. Ilyas , and P. Papotti . 2013b. Holistic data cleaning: Putting violations into context . In Proceedings of the 29th International Conference on Data Engineering , pp. 458 -- 469 . 7, 150, 151, 163, 164, 166, 179, 183 X. Chu, I. F. Ilyas, and P. Papotti. 2013b. Holistic data cleaning: Putting violations into context. In Proceedings of the 29th International Conference on Data Engineering, pp. 458--469. 7, 150, 151, 163, 164, 166, 179, 183"},{"key":"e_1_4_1_58_1","first-page":"1222","volume-title":"Proceedings of the 30th International Conference on Data Engineering","author":"Chu X.","unstructured":"X. Chu , I. F. Ilyas , P. Papotti , and Y. Ye . 2014. Ruleminer: Data quality rules discovery . In Proceedings of the 30th International Conference on Data Engineering , pp. 1222 -- 1225 . 134 X. Chu, I. F. Ilyas, P. Papotti, and Y. Ye. 2014. Ruleminer: Data quality rules discovery. In Proceedings of the 30th International Conference on Data Engineering, pp. 1222--1225. 134"},{"key":"e_1_4_1_59_1","first-page":"1247","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Chu X.","unstructured":"X. Chu , J. Morcos , I. F. Ilyas , M. Ouzzani , P. Papotti , N. Tang , and Y. Ye . 2015. KATARA: A data cleaning system powered by knowledge bases and crowdsourcing . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 1247 -- 1261 . 164, 184, 187, 188, 206 X. Chu, J. Morcos, I. F. Ilyas, M. Ouzzani, P. Papotti, N. Tang, and Y. Ye. 2015. KATARA: A data cleaning system powered by knowledge bases and crowdsourcing. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 1247--1261. 164, 184, 187, 188, 206"},{"key":"e_1_4_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/2983200.2983203"},{"key":"e_1_4_1_61_1","first-page":"315","volume-title":"Proceedings of the 33rd International Conference on Very Large Data Bases","author":"Cong G.","unstructured":"G. Cong , W. Fan , F. Geerts , X. Jia , and S. Ma . 2007. Improving data quality: Consistency and accuracy . In Proceedings of the 33rd International Conference on Very Large Data Bases , pp. 315 -- 326 . 163, 164, 166, 179, 185 G. Cong, W. Fan, F. Geerts, X. Jia, and S. Ma. 2007. Improving data quality: Consistency and accuracy. In Proceedings of the 33rd International Conference on Very Large Data Bases, pp. 315--326. 163, 164, 166, 179, 185"},{"key":"e_1_4_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2912091"},{"key":"e_1_4_1_63_1","unstructured":"A. Cypher and D. C. Halbert. 1993. Watch What I do: Programming by Demonstration. MIT Press. 102  A. Cypher and D. C. Halbert. 1993. Watch What I do: Programming by Demonstration. MIT Press. 102"},{"key":"e_1_4_1_64_1","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1145\/2463676.2465327","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Dallachiesa M.","year":"2013","unstructured":"M. Dallachiesa , A. Ebaid , A. Eldawy , A. Elmagarmid , I. F. Ilyas , M. Ouzzani , and N. Tang . 2013. Nadeef: a commodity data cleaning system . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 541 -- 552 , 2013 . 164, 166 M. Dallachiesa, A. Ebaid, A. Eldawy, A. Elmagarmid, I. F. Ilyas, M. Ouzzani, and N. Tang. 2013. Nadeef: a commodity data cleaning system. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 541--552, 2013. 164, 166"},{"key":"e_1_4_1_65_1","doi-asserted-by":"crossref","unstructured":"T. Dasu and T. Johnson. 2003. Exploratory Data Mining and Data Cleaning. J. Wiley & Sons Inc. 2  T. Dasu and T. Johnson. 2003. Exploratory Data Mining and Data Cleaning. J. Wiley & Sons Inc. 2","DOI":"10.1002\/0471448354"},{"key":"e_1_4_1_66_1","first-page":"1313","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"2","author":"Davy M.","unstructured":"M. Davy and S. Godsill . 2002. Detection of abrupt spectral changes using support vector machines an application to audio signal segmentation . In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , volume 2 , pp. II-- 1313 . IEEE. 32 M. Davy and S. Godsill. 2002. Detection of abrupt spectral changes using support vector machines an application to audio signal segmentation. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, volume 2, pp. II--1313. IEEE. 32"},{"key":"e_1_4_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-007-0048-x"},{"key":"e_1_4_1_68_1","volume-title":"Proceedings of the 22nd International Conference on Database Theory. 8, 203","author":"Sa C. De","unstructured":"C. De Sa , I. F. Ilyas , B. Kimelfeld , C. R\u00e9 , and T. Rekatsinas . 2019. A formal framework for probabilistic unclean databases . In Proceedings of the 22nd International Conference on Database Theory. 8, 203 , 204, 205, 211 C. De Sa, I. F. Ilyas, B. Kimelfeld, C. R\u00e9, and T. Rekatsinas. 2019. A formal framework for probabilistic unclean databases. In Proceedings of the 22nd International Conference on Database Theory. 8, 203, 204, 205, 211"},{"key":"e_1_4_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/5326.827457"},{"key":"e_1_4_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_4_1_71_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_4_1_72_1","first-page":"27","volume-title":"Proceedings of the 18th International Conference on Very Large Data Bases","author":"DeWitt D. J","year":"1992","unstructured":"D. J DeWitt , J. F Naughton , D. A. Schneider , and S. Seshadri . 1992. Practical skew handling in parallel joins . In Proceedings of the 18th International Conference on Very Large Data Bases , pp. 27 -- 40 , 1992 . 67 D. J DeWitt, J. F Naughton, D. A. Schneider, and S. Seshadri. 1992. Practical skew handling in parallel joins. In Proceedings of the 18th International Conference on Very Large Data Bases, pp. 27--40, 1992. 67"},{"key":"e_1_4_1_73_1","first-page":"1","volume-title":"10th International Workshop on Quality in Databases","author":"Diallo T.","unstructured":"T. Diallo , J.-M. Petit , and S. Servigne . 2012. Discovering editing rules for data cleaning . In 10th International Workshop on Quality in Databases , pp. 1 -- 8 . 144 T. Diallo, J.-M. Petit, and S. Servigne. 2012. Discovering editing rules for data cleaning. In 10th International Workshop on Quality in Databases, pp. 1--8. 144"},{"key":"e_1_4_1_74_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454226"},{"key":"e_1_4_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2003.1234770"},{"key":"e_1_4_1_76_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687620"},{"key":"e_1_4_1_77_1","doi-asserted-by":"crossref","unstructured":"X. L. Dong and D. Srivastava. 2015. Big Data Integration. Synthesis Lectures on Data Management. Morgan & Claypool. 79  X. L. Dong and D. Srivastava. 2015. Big Data Integration. Synthesis Lectures on Data Management. Morgan & Claypool. 79","DOI":"10.1007\/978-3-031-01853-4"},{"key":"e_1_4_1_78_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687690"},{"key":"e_1_4_1_79_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687691"},{"key":"e_1_4_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.250581"},{"key":"e_1_4_1_81_1","first-page":"834","volume-title":"Proceedings of the 46th Annual Meeting Association for Computational Linguistics","author":"Elsner M.","unstructured":"M. Elsner and E. Charniak . 2008. You talking to me? A corpus and algorithm for conversation disentanglement . In Proceedings of the 46th Annual Meeting Association for Computational Linguistics , pp. 834 -- 842 . 60 M. Elsner and E. Charniak. 2008. You talking to me? A corpus and algorithm for conversation disentanglement. In Proceedings of the 46th Annual Meeting Association for Computational Linguistics, pp. 834--842. 60"},{"key":"e_1_4_1_82_1","first-page":"19","volume-title":"Proceedings of the Workshop on Integer Linear Programming for Natural Language Processing","author":"Elsner M.","unstructured":"M. Elsner and W. Schudy . 2009. Bounding and comparing methods for correlation clustering beyond ILP . In Proceedings of the Workshop on Integer Linear Programming for Natural Language Processing , pp. 19 -- 27 . 6, 58, 59 M. Elsner and W. Schudy. 2009. Bounding and comparing methods for correlation clustering beyond ILP. In Proceedings of the Workshop on Integer Linear Programming for Natural Language Processing, pp. 19--27. 6, 58, 59"},{"key":"e_1_4_1_83_1","doi-asserted-by":"publisher","DOI":"10.5555\/1085304.1085309"},{"key":"e_1_4_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/1114244.1114249"},{"key":"e_1_4_1_85_1","first-page":"198","volume-title":"Proceedings of the 28th International Conference on Conceptual Modeling","author":"Fagin R.","unstructured":"R. Fagin , L. M. Haas , M. Hern\u00e1ndez , R. J. Miller , L. Popa , and Y. Velegrakis . 2009. Clio: Schema mapping creation and data exchange . In Proceedings of the 28th International Conference on Conceptual Modeling , pp. 198 -- 236 . Springer. 117 R. Fagin, L. M. Haas, M. Hern\u00e1ndez, R. J. Miller, L. Popa, and Y. Velegrakis. 2009. Clio: Schema mapping creation and data exchange. In Proceedings of the 28th International Conference on Conceptual Modeling, pp. 198--236. Springer. 117"},{"key":"e_1_4_1_86_1","first-page":"125","volume-title":"Proceedings of the 15th International Conference on Web-Age Information Management","author":"Fan G.","unstructured":"G. Fan , W. Fan , and F. Geerts . 2014a. Detecting errors in numeric attributes . In Proceedings of the 15th International Conference on Web-Age Information Management , pp. 125 -- 137 . Springer. 139, 141, 142 G. Fan, W. Fan, and F. Geerts. 2014a. Detecting errors in numeric attributes. In Proceedings of the 15th International Conference on Web-Age Information Management, pp. 125--137. Springer. 139, 141, 142"},{"key":"e_1_4_1_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-003-0132-7"},{"key":"e_1_4_1_88_1","first-page":"178","article-title":"Foundations of Data Quality Management","volume":"2","author":"Fan W.","year":"2012","unstructured":"W. Fan and F. Geerts . 2012 . Foundations of Data Quality Management . Synthesis Lectures on Data Management. 2 , 7, 178 W. Fan and F. Geerts. 2012. Foundations of Data Quality Management. Synthesis Lectures on Data Management. 2, 7, 178","journal-title":"Synthesis Lectures on Data Management."},{"key":"e_1_4_1_89_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687674"},{"key":"e_1_4_1_90_1","volume-title":"Proceedings of the VLDB Endowment, 3(1--2): 173--184","author":"Fan W.","unstructured":"W. Fan , J. Li , S. Ma , N. Tang , and W. Yu . 2010. Towards certain fixes with editing rules and master data . Proceedings of the VLDB Endowment, 3(1--2): 173--184 . 139, 143, 163, 164, 184, 186, 187 W. Fan, J. Li, S. Ma, N. Tang, and W. Yu. 2010. Towards certain fixes with editing rules and master data. Proceedings of the VLDB Endowment, 3(1--2): 173--184. 139, 143, 163, 164, 184, 186, 187"},{"key":"e_1_4_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.154"},{"key":"e_1_4_1_92_1","first-page":"469","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Fan W.","unstructured":"W. Fan , J. Li , S. Ma , N. Tang , and W. Yu . 2011b. Interaction between record matching and data repairing . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 469 -- 480 . 164, 166, 170, 171 W. Fan, J. Li, S. Ma, N. Tang, and W. Yu. 2011b. Interaction between record matching and data repairing. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 469--480. 164, 166, 170, 171"},{"key":"e_1_4_1_93_1","first-page":"1","article-title":"Conflict resolution with data currency and consistency","volume":"6","author":"Fan W.","year":"2014","unstructured":"W. Fan , F. Geerts , N. Tang , and W. Yu . 2014 b. Conflict resolution with data currency and consistency . Journal of Data and Information Quality, 5(1--2) : 6 : 1 -- 6 :37. 166 W. Fan, F. Geerts, N. Tang, and W. Yu. 2014b. Conflict resolution with data currency and consistency. Journal of Data and Information Quality, 5(1--2): 6:1--6:37. 166","journal-title":"Journal of Data and Information Quality, 5(1--2)"},{"key":"e_1_4_1_94_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1969.10501049"},{"key":"e_1_4_1_95_1","doi-asserted-by":"publisher","DOI":"10.5555\/1216155.1216159"},{"key":"e_1_4_1_96_1","unstructured":"I. K. Fodor. 2002. A survey of dimension reduction techniques. Technical report Lawrence Livermore National Lab. CA (US). 32  I. K. Fodor. 2002. A survey of dimension reduction techniques. Technical report Lawrence Livermore National Lab. CA (US). 32"},{"key":"e_1_4_1_97_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"e_1_4_1_98_1","doi-asserted-by":"crossref","unstructured":"Y. Freund H. S. Seung E. Shamir and N. Tishby. 1997. Selective sampling using the query by committee algorithm. Machine Learning 28(2--3): 133--168. 199  Y. Freund H. S. Seung E. Shamir and N. Tishby. 1997. Selective sampling using the query by committee algorithm. Machine Learning 28(2--3): 133--168. 199","DOI":"10.1023\/A:1007330508534"},{"key":"e_1_4_1_99_1","volume-title":"The Elements of Statistical Learning","volume":"1","author":"Friedman J.","unstructured":"J. Friedman , T. Hastie , and R. Tibshirani . 2001 . The Elements of Statistical Learning , volume 1 . Springer. 56 J. Friedman, T. Hastie, and R. Tibshirani. 2001. The Elements of Statistical Learning, volume 1. Springer. 56"},{"key":"e_1_4_1_100_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb047069"},{"key":"e_1_4_1_101_1","first-page":"371","volume-title":"Proceedings of the 27th International Conference on Very Large Data Bases","author":"Galhardas H.","year":"2001","unstructured":"H. Galhardas , D. Florescu , D. Shasha , E. Simon , and C.-A. Saita . 2001 . Declarative data cleaning: Language, model, and algorithms . In Proceedings of the 27th International Conference on Very Large Data Bases , pp. 371 -- 380 . 85 H. Galhardas, D. Florescu, D. Shasha, E. Simon, and C.-A. Saita. 2001. Declarative data cleaning: Language, model, and algorithms. In Proceedings of the 27th International Conference on Very Large Data Bases, pp. 371--380. 85"},{"key":"e_1_4_1_102_1","first-page":"136","volume-title":"Proceedings of the 13th International Conference Data Warehousing and Knowledge Discovery","author":"Galhardas H.","unstructured":"H. Galhardas , A. Lopes , and E. Santos . 2011. Support for user involvement in data cleaning . In Proceedings of the 13th International Conference Data Warehousing and Knowledge Discovery , pp. 136 -- 151 . 85 H. Galhardas, A. Lopes, and E. Santos. 2011. Support for user involvement in data cleaning. In Proceedings of the 13th International Conference Data Warehousing and Knowledge Discovery, pp. 136--151. 85"},{"key":"e_1_4_1_103_1","first-page":"945","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Gan E.","unstructured":"E. Gan and P. Bailis . 2017. Scalable kernel density classification via threshold-based pruning . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 945 -- 959 . ACM. 25 E. Gan and P. Bailis. 2017. Scalable kernel density classification via threshold-based pruning. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 945--959. ACM. 25"},{"key":"e_1_4_1_104_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00523ED1V01Y201307DTM036"},{"key":"e_1_4_1_105_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536363"},{"key":"e_1_4_1_106_1","first-page":"232","volume-title":"Proceedings of the of the 30th International Conference on Data Engineering","author":"Geerts F.","unstructured":"F. Geerts , G. Mecca , P. Papotti , and D. Santoro . 2014a. Mapping and cleaning . In Proceedings of the of the 30th International Conference on Data Engineering , pp. 232 -- 243 . 169 F. Geerts, G. Mecca, P. Papotti, and D. Santoro. 2014a. Mapping and cleaning. In Proceedings of the of the 30th International Conference on Data Engineering, pp. 232--243. 169"},{"key":"e_1_4_1_107_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733031"},{"key":"e_1_4_1_108_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"e_1_4_1_109_1","first-page":"601","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Gokhale C.","unstructured":"C. Gokhale , S. Das , A. Doan , J. F Naughton , N. Rampalli , J. Shavlik , and X. Zhu . 2014. Corleone: Hands-off crowdsourcing for entity matching . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 601 -- 612 . 84 C. Gokhale, S. Das, A. Doan, J. F Naughton, N. Rampalli, J. Shavlik, and X. Zhu. 2014. Corleone: Hands-off crowdsourcing for entity matching. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 601--612. 84"},{"key":"e_1_4_1_110_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453900"},{"key":"e_1_4_1_111_1","volume-title":"Deep Learning","volume":"1","author":"Goodfellow I.","unstructured":"I. Goodfellow , Y. Bengio , and A. Courville . 2016 . Deep Learning , vol. 1 . MIT press Cambridge. 212 I. Goodfellow, Y. Bengio, and A. Courville. 2016. Deep Learning, vol. 1. MIT press Cambridge. 212"},{"key":"e_1_4_1_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/1346330.1346334"},{"key":"e_1_4_1_113_1","volume-title":"The problem of incomplete information in relational databases","author":"Grahne G.","unstructured":"G. Grahne . 1991. The problem of incomplete information in relational databases , volume 554 . Springer Science +Business Media. 2 G. Grahne. 1991. The problem of incomplete information in relational databases, volume 554. Springer Science+Business Media. 2"},{"key":"e_1_4_1_114_1","doi-asserted-by":"crossref","unstructured":"S. Greco C. Molinaro and F. Spezzano. 2012. Incomplete data and data dependencies in relational databases. Synthesis Lectures on Data Management. 2  S. Greco C. Molinaro and F. Spezzano. 2012. Incomplete data and data dependencies in relational databases. Synthesis Lectures on Data Management. 2","DOI":"10.1007\/978-3-031-01893-0"},{"key":"e_1_4_1_115_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1969.10490657"},{"key":"e_1_4_1_116_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732939.2732943"},{"key":"e_1_4_1_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/1926385.1926423"},{"key":"e_1_4_1_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/2240236.2240260"},{"key":"e_1_4_1_119_1","volume-title":"Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology. 94","author":"Guo P. J","unstructured":"P. J Guo , S. Kandel , J. Hellerstein , and J. Heer . 2011. Proactive wrangling: Mixed-initiative end-user programming of data transformation scripts . In Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology. 94 , 100, 106 P. J Guo, S. Kandel, J. Hellerstein, and J. Heer. 2011. Proactive wrangling: Mixed-initiative end-user programming of data transformation scripts. In Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology. 94, 100, 106"},{"key":"e_1_4_1_120_1","first-page":"805","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Haas L. M.","unstructured":"L. M. Haas , M. A. Hern\u00e1ndez , H. Ho , L. Popa , and M. Roth . 2005. Clio grows up: from research prototype to industrial tool . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 805 -- 810 . 139 L. M. Haas, M. A. Hern\u00e1ndez, H. Ho, L. Popa, and M. Roth. 2005. Clio grows up: from research prototype to industrial tool. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 805--810. 139"},{"key":"e_1_4_1_121_1","volume-title":"Robust Statistics: the Approach Based on Influence Functions","volume":"114","author":"Hampel F. R.","unstructured":"F. R. Hampel , E. M. Ronchetti , P. J Rousseeuw , and W. A. Stahel . 2011 . Robust Statistics: the Approach Based on Influence Functions , volume 114 . J. Wiley & Sons. 20 F. R. Hampel, E. M. Ronchetti, P. J Rousseeuw, and W. A. Stahel. 2011. Robust Statistics: the Approach Based on Influence Functions, volume 114. J. Wiley & Sons. 20"},{"key":"e_1_4_1_122_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687771"},{"key":"e_1_4_1_123_1","first-page":"195","article-title":"Identification of Outliers, volume 11","volume":"4","author":"Hawkins D.","year":"1980","unstructured":"D. Hawkins . 1980 . Identification of Outliers, volume 11 . Chapman and Hall. 4 , 11, 195 D. Hawkins. 1980. Identification of Outliers, volume 11. Chapman and Hall. 4, 11, 195","journal-title":"Chapman and Hall."},{"key":"e_1_4_1_124_1","first-page":"170","volume-title":"Proceedings of the 4th International Conference Data Warehousing and Knowledge Discovery","author":"Hawkins S.","unstructured":"S. Hawkins , H. He , G. Williams , and R. Baxter . 2002. Outlier detection using replicator neural networks . In Proceedings of the 4th International Conference Data Warehousing and Knowledge Discovery , pp. 170 -- 180 . Springer. 32, 195 S. Hawkins, H. He, G. Williams, and R. Baxter. 2002. Outlier detection using replicator neural networks. In Proceedings of the 4th International Conference Data Warehousing and Knowledge Discovery, pp. 170--180. Springer. 32, 195"},{"issue":"1","key":"e_1_4_1_125_1","first-page":"1","article-title":"Predictive interaction for data transformation. In Proceedings of the 7th Biennial Conf. on Innovative Data Systems Research","volume":"10","author":"Heer J.","year":"2015","unstructured":"J. Heer , J. Hellerstein , and S. Kandel . 2015 . Predictive interaction for data transformation. In Proceedings of the 7th Biennial Conf. on Innovative Data Systems Research . DOI : 10 . 1 . 1 .692.1613. 94, 100 J. Heer, J. Hellerstein, and S. Kandel. 2015. Predictive interaction for data transformation. In Proceedings of the 7th Biennial Conf. on Innovative Data Systems Research. DOI: 10.1.1.692.1613. 94, 100","journal-title":"DOI"},{"key":"e_1_4_1_126_1","unstructured":"J. M. Hellerstein. 2008. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe (UNECE). 1 2 19 44  J. M. Hellerstein. 2008. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe (UNECE). 1 2 19 44"},{"key":"e_1_4_1_127_1","doi-asserted-by":"publisher","DOI":"10.1145\/568271.223807"},{"key":"e_1_4_1_128_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009761603038"},{"key":"e_1_4_1_129_1","first-page":"113","volume-title":"Proceedings of the 26th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems","author":"Hernich A.","unstructured":"A. Hernich and N. Schweikardt . 2007. CWA-solutions for data exchange settings with target dependencies . In Proceedings of the 26th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems , pp. 113 -- 122 . ACM. 117 A. Hernich and N. Schweikardt. 2007. CWA-solutions for data exchange settings with target dependencies. In Proceedings of the 26th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 113--122. ACM. 117"},{"key":"e_1_4_1_130_1","unstructured":"T. N. Herzog F. J. Scheuren and W. E. Winkler. 2007. Data Quality and Record Linkage Techniques. Springer Science+Business Media. 2 48  T. N. Herzog F. J. Scheuren and W. E. Winkler. 2007. Data Quality and Record Linkage Techniques. Springer Science+Business Media. 2 48"},{"key":"e_1_4_1_131_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000045502.10941.a9"},{"key":"e_1_4_1_132_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0071325"},{"key":"e_1_4_1_133_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/42.2.100"},{"key":"e_1_4_1_134_1","unstructured":"B. Iglewicz and D. C. Hoaglin. 1993. How to detect and handle outliers volume 16. ASQC Quality Press. 19  B. Iglewicz and D. C. Hoaglin. 1993. How to detect and handle outliers volume 16. ASQC Quality Press. 19"},{"key":"e_1_4_1_135_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000045"},{"key":"e_1_4_1_136_1","volume-title":"Proceedings of the 31st International Conference on Data Engineering. 139","author":"Interlandi M.","unstructured":"M. Interlandi and N. Tang . 2015. Proof positive and negative in data cleaning . In Proceedings of the 31st International Conference on Data Engineering. 139 , 145, 146 M. Interlandi and N. Tang. 2015. Proof positive and negative in data cleaning. In Proceedings of the 31st International Conference on Data Engineering. 139, 145, 146"},{"key":"e_1_4_1_137_1","volume-title":"Proceedings of the 4th Biennial Conf. on Innovative Data Systems Research","author":"Ives Z.","year":"2009","unstructured":"Z. Ives , C. Knoblock , S. Minton , M. Jacob , P. Talukdar , R. Tuchinda , J. L. Ambite , M. Muslea , and C. Gazen . 2009. Interactive data integration through smart copy & paste . In Proceedings of the 4th Biennial Conf. on Innovative Data Systems Research , 2009 . 102 Z. Ives, C. Knoblock, S. Minton, M. Jacob, P. Talukdar, R. Tuchinda, J. L. Ambite, M. Muslea, and C. Gazen. 2009. Interactive data integration through smart copy & paste. In Proceedings of the 4th Biennial Conf. on Innovative Data Systems Research, 2009. 102"},{"key":"e_1_4_1_138_1","volume-title":"Unimatch: A record linkage system: User's manual","author":"Jaro M. A.","unstructured":"M. A. Jaro . 1976. Unimatch: A record linkage system: User's manual . U.S. Bureau of the Census. 51 M. A. Jaro. 1976. Unimatch: A record linkage system: User's manual. U.S. Bureau of the Census. 51"},{"key":"e_1_4_1_139_1","first-page":"293","volume-title":"Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Jin W.","unstructured":"W. Jin , A. K. H. Tung , and J. Han . 2001. Mining top-n local outliers in large databases . In Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pp. 293 -- 298 . 30 W. Jin, A. K. H. Tung, and J. Han. 2001. Mining top-n local outliers in large databases. In Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 293--298. 30"},{"key":"e_1_4_1_140_1","first-page":"577","volume-title":"10th Pacific-Asia Conf.","author":"Jin W.","unstructured":"W. Jin , A. K. H. Tung , J. Han , and W. Wang . 2006. Ranking outliers using symmetric neighborhood relationship. In Advances in Knowledge Discovery and Data Mining , 10th Pacific-Asia Conf. , pp. 577 -- 593 . 30 W. Jin, A. K. H. Tung, J. Han, and W. Wang. 2006. Ranking outliers using symmetric neighborhood relationship. In Advances in Knowledge Discovery and Data Mining, 10th Pacific-Asia Conf., pp. 577--593. 30"},{"key":"e_1_4_1_141_1","first-page":"107","article-title":"Foofah: Transforming data by example. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 683--698","volume":"91","author":"Jin Z.","year":"2017","unstructured":"Z. Jin , M. R. Anderson , M. Cafarella , and H.V. Jagadish . 2017 . Foofah: Transforming data by example. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 683--698 . ACM. 91 , 107 Z. Jin, M. R. Anderson, M. Cafarella, and H.V. Jagadish. 2017. Foofah: Transforming data by example. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 683--698. ACM. 91, 107","journal-title":"ACM."},{"key":"e_1_4_1_142_1","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375673"},{"key":"e_1_4_1_143_1","first-page":"3363","volume-title":"Proceedings of the SIGCHI Conf. on Human Factors in Computing Systems","author":"Kandel S.","unstructured":"S. Kandel , A. Paepcke , J. Hellerstein , and J. Heer . 2011. Wrangler: Interactive visual specification of data transformation scripts . In Proceedings of the SIGCHI Conf. on Human Factors in Computing Systems , pp. 3363 -- 3372 . 91, 93, 94, 95, 100 S. Kandel, A. Paepcke, J. Hellerstein, and J. Heer. 2011. Wrangler: Interactive visual specification of data transformation scripts. In Proceedings of the SIGCHI Conf. on Human Factors in Computing Systems, pp. 3363--3372. 91, 93, 94, 95, 100"},{"key":"e_1_4_1_144_1","first-page":"1215","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Khayyat Z.","unstructured":"Z. Khayyat , I. F. Ilyas , A. Jindal , S. Madden , M. Ouzzani , P. Papotti , J.-A. Quian\u00e9-Ruiz , N. Tang , and S. Yin . 2015. BigDansing: A system for big data cleansing . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 1215 -- 1230 . 151, 160 Z. Khayyat, I. F. Ilyas, A. Jindal, S. Madden, M. Ouzzani, P. Papotti, J.-A. Quian\u00e9-Ruiz, N. Tang, and S. Yin. 2015. BigDansing: A system for big data cleansing. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 1215--1230. 151, 160"},{"key":"e_1_4_1_145_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-014-5443-2"},{"key":"e_1_4_1_146_1","first-page":"392","volume-title":"Proceedings of the 24th International Conference on Very Large Data Bases","author":"Knorr E. M","unstructured":"E. M Knorr and R. T. Ng . 1998. Algorithms for mining distance-based outliers in large datasets . In Proceedings of the 24th International Conference on Very Large Data Bases , pp. 392 -- 403 . 14, 26, 27, 28 E. M Knorr and R. T. Ng. 1998. Algorithms for mining distance-based outliers in large datasets. In Proceedings of the 24th International Conference on Very Large Data Bases, pp. 392--403. 14, 26, 27, 28"},{"key":"e_1_4_1_147_1","first-page":"211","volume-title":"Proceedings of the 25th International Conference on Very Large Data Bases","volume":"99","author":"Knorr E. M","unstructured":"E. M Knorr and R. T. Ng . 1999. Finding intensional knowledge of distance-based outliers . In Proceedings of the 25th International Conference on Very Large Data Bases , volume 99 , pp. 211 -- 222 . 14, 26, 27 E. M Knorr and R. T. Ng. 1999. Finding intensional knowledge of distance-based outliers. In Proceedings of the 25th International Conference on Very Large Data Bases, volume 99, pp. 211--222. 14, 26, 27"},{"key":"e_1_4_1_148_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514894.1514901"},{"key":"e_1_4_1_149_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142351.1142357"},{"key":"e_1_4_1_150_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367527"},{"key":"e_1_4_1_151_1","first-page":"618","volume-title":"Proceedings of the 28th International Conference on Data Engineering","author":"Kolb L.","unstructured":"L. Kolb , A. Thor , and E. Rahm . 2012b. Load balancing for MapReduce-based entity resolution . In Proceedings of the 28th International Conference on Data Engineering , pp. 618 -- 629 . 67 L. Kolb, A. Thor, and E. Rahm. 2012b. Load balancing for MapReduce-based entity resolution. In Proceedings of the 28th International Conference on Data Engineering, pp. 618--629. 67"},{"key":"e_1_4_1_152_1","unstructured":"D. Koller and N. Friedman. 2009. Probabilistic Graphical Models: Principles and Techniques. The MIT Press. 196 205 208  D. Koller and N. Friedman. 2009. Probabilistic Graphical Models: Principles and Techniques. The MIT Press. 196 205 208"},{"key":"e_1_4_1_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2003.1232271"},{"key":"e_1_4_1_154_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994535"},{"key":"e_1_4_1_155_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920904"},{"key":"e_1_4_1_156_1","first-page":"614","volume-title":"Proceedings of the SIAM International Conference on Data Mining","author":"Kou Y.","unstructured":"Y. Kou , C.-T. Lu , and D. Chen . 2006. Spatial weighted outlier detection . In Proceedings of the SIAM International Conference on Data Mining , pp. 614 -- 618 . SIAM. 40 Y. Kou, C.-T. Lu, and D. Chen. 2006. Spatial weighted outlier detection. In Proceedings of the SIAM International Conference on Data Mining, pp. 614--618. SIAM. 40"},{"key":"e_1_4_1_157_1","first-page":"802","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Koudas N.","unstructured":"N. Koudas , S. Sarawagi , and D. Srivastava . 2006. Record linkage: similarity measures and algorithms . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 802 -- 803 . 2, 48 N. Koudas, S. Sarawagi, and D. Srivastava. 2006. Record linkage: similarity measures and algorithms. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 802--803. 2, 48"},{"key":"e_1_4_1_158_1","first-page":"1275","volume-title":"Proceedings of the 25th International Conference on Data Engineering","author":"Koudas N.","unstructured":"N. Koudas , A. Saha , D. Srivastava , and S. Venkatasubramanian . 2009. Metric functional dependencies . In Proceedings of the 25th International Conference on Data Engineering , pp. 1275 -- 1278 . 138, 141 N. Koudas, A. Saha, D. Srivastava, and S. Venkatasubramanian. 2009. Metric functional dependencies. In Proceedings of the 25th International Conference on Data Engineering, pp. 1275--1278. 138, 141"},{"key":"e_1_4_1_159_1","first-page":"831","volume-title":"13th Pacific-Asia Conf.","author":"Kriegel H.-P.","unstructured":"H.-P. Kriegel , P. Kr\u00f6ger , E. Schubert , and A. Zimek . 2009. Outlier detection in axis-parallel subspaces of high dimensional data. In Advances in Knowledge Discovery and Data Mining , 13th Pacific-Asia Conf. , pp. 831 -- 838 . Springer. 33, 37, 39 H.-P. Kriegel, P. Kr\u00f6ger, E. Schubert, and A. Zimek. 2009. Outlier detection in axis-parallel subspaces of high dimensional data. In Advances in Knowledge Discovery and Data Mining, 13th Pacific-Asia Conf., pp. 831--838. Springer. 33, 37, 39"},{"key":"e_1_4_1_160_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"e_1_4_1_161_1","doi-asserted-by":"publisher","DOI":"10.1145\/503099.503102"},{"key":"e_1_4_1_162_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_4_1_163_1","volume-title":"Testing Statistical Hypotheses","author":"Lehmann E. L.","unstructured":"E. L. Lehmann and J. P Romano . 2006. Testing Statistical Hypotheses . Springer Science +Business Media. 16 E. L. Lehmann and J. P Romano. 2006. Testing Statistical Hypotheses. Springer Science+Business Media. 16"},{"key":"e_1_4_1_164_1","doi-asserted-by":"crossref","unstructured":"J. Leskovec A. Rajaraman and J. D. Ullman. 2014. Mining of Massive Datasets. Cambridge University Press. 62 63  J. Leskovec A. Rajaraman and J. D. Ullman. 2014. Mining of Massive Datasets. Cambridge University Press. 62 63","DOI":"10.1017\/CBO9781139924801"},{"key":"e_1_4_1_165_1","first-page":"707","volume-title":"Soviet Physics Doklady","volume":"10","author":"Levenshtein V.I.","year":"1966","unstructured":"V.I. Levenshtein . 1966 . Binary codes capable of correcting deletions, insertions and reversals . In Soviet Physics Doklady , volume 10 , page 707 . 49 V.I. Levenshtein. 1966. Binary codes capable of correcting deletions, insertions and reversals. In Soviet Physics Doklady, volume 10, page 707. 49"},{"key":"e_1_4_1_166_1","first-page":"43","article-title":"Robust contextual outlier detection: Where context meets sparsity. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pp. 2167--2172","volume":"33","author":"Liang J.","year":"2016","unstructured":"J. Liang and S. Parthasarathy . 2016 . Robust contextual outlier detection: Where context meets sparsity. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pp. 2167--2172 . ACM. 33 , 40, 43 J. Liang and S. Parthasarathy. 2016. Robust contextual outlier detection: Where context meets sparsity. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pp. 2167--2172. ACM. 33, 40, 43","journal-title":"ACM."},{"key":"e_1_4_1_167_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142351.1142360"},{"key":"e_1_4_1_168_1","first-page":"179","volume-title":"Proceedings of the 11th International Conference on Database Theory","author":"Lopatenko A.","unstructured":"A. Lopatenko and L. E. Bertossi . 2007. Complexity of consistent query answering in databases under cardinality-based and incremental repair semantics . In Proceedings of the 11th International Conference on Database Theory , pp. 179 -- 193 . 179, 191 A. Lopatenko and L. E. Bertossi. 2007. Complexity of consistent query answering in databases under cardinality-based and incremental repair semantics. In Proceedings of the 11th International Conference on Database Theory, pp. 179--193. 179, 191"},{"key":"e_1_4_1_169_1","doi-asserted-by":"crossref","first-page":"1741","DOI":"10.1109\/IJCNN.2003.1223670","volume-title":"Neural Networks, 2003 Proceedings of the International Joint Conference on","volume":"3","author":"Ma J.","unstructured":"J. Ma and S. Perkins . 2003. Time-series novelty detection using one-class support vector machines . In Neural Networks, 2003 Proceedings of the International Joint Conference on , volume 3 , pp. 1741 -- 1745 . IEEE. 32 J. Ma and S. Perkins. 2003. Time-series novelty detection using one-class support vector machines. In Neural Networks, 2003 Proceedings of the International Joint Conference on, volume 3, pp. 1741--1745. IEEE. 32"},{"key":"e_1_4_1_170_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2013.11.002"},{"key":"e_1_4_1_171_1","first-page":"49","article-title":"On the generalized distance in statistics","volume":"2","author":"Mahalanobis P. C.","year":"1936","unstructured":"P. C. Mahalanobis . 1936 . On the generalized distance in statistics . Proceedings of the National Institute of Sciences (Calcutta) , 2 : 49 -- 55 . 21 P. C. Mahalanobis. 1936. On the generalized distance in statistics. Proceedings of the National Institute of Sciences (Calcutta), 2:49--55. 21","journal-title":"Proceedings of the National Institute of Sciences (Calcutta)"},{"key":"e_1_4_1_172_1","doi-asserted-by":"publisher","DOI":"10.1145\/320107.320115"},{"key":"e_1_4_1_173_1","first-page":"75","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Mayfield C.","unstructured":"C. Mayfield , J. Neville , and S. Prabhakar . 2010. Eracer: A database approach for statistical inference and data cleaning . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 75 -- 86 . 208 C. Mayfield, J. Neville, and S. Prabhakar. 2010. Eracer: A database approach for statistical inference and data cleaning. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 75--86. 208"},{"key":"e_1_4_1_174_1","first-page":"905","article-title":"Conditional models of identity uncertainty with application to noun coreference","author":"McCallum A.","year":"2004","unstructured":"A. McCallum and B. Wellner . 2004 . Conditional models of identity uncertainty with application to noun coreference . In Advances in Neural Information Proc Systems 17, Proc. Neural Information Proc. Systems , pp. 905 -- 912 . 205 A. McCallum and B. Wellner. 2004. Conditional models of identity uncertainty with application to noun coreference. In Advances in Neural Information Proc Systems 17, Proc. Neural Information Proc. Systems, pp. 905--912. 205","journal-title":"Advances in Neural Information Proc Systems 17, Proc. Neural Information Proc. Systems"},{"key":"e_1_4_1_175_1","first-page":"505","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Meliou A.","unstructured":"A. Meliou , W. Gatterbauer , S. Nath , and D. Suciu . 2011. Tracing data errors with view-conditioned causality . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 505 -- 516 . 151, 153, 154, 155 A. Meliou, W. Gatterbauer, S. Nath, and D. Suciu. 2011. Tracing data errors with view-conditioned causality. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 505--516. 151, 153, 154, 155"},{"key":"e_1_4_1_176_1","first-page":"440","volume-title":"Proceedings of the 21st National Conf. on Artificial Intelligence and 18th Innovative Applications of Artificial Intelligence Conf.","volume":"21","author":"Michelson M.","unstructured":"M. Michelson and C. A. Knoblock . 2006. Learning blocking schemes for record linkage . In Proceedings of the 21st National Conf. on Artificial Intelligence and 18th Innovative Applications of Artificial Intelligence Conf. , volume 21 , page 440 . 62 M. Michelson and C. A. Knoblock. 2006. Learning blocking schemes for record linkage. In Proceedings of the 21st National Conf. on Artificial Intelligence and 18th Innovative Applications of Artificial Intelligence Conf., volume 21, page 440. 62"},{"key":"e_1_4_1_177_1","first-page":"267","volume-title":"Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining","author":"Monge A. E.","unstructured":"A. E. Monge and C. Elkan . 1996. The field matching problem: Algorithms and applications . In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining , pp. 267 -- 270 . 55 A. E. Monge and C. Elkan. 1996. The field matching problem: Algorithms and applications. In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, pp. 267--270. 55"},{"key":"e_1_4_1_178_1","first-page":"19","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Mudgal S.","unstructured":"S. Mudgal , H. Li , T. Rekatsinas , A. Doan , Y. Park , G. Krishnan , R. Deep , E. Arcaute , and V. Raghavendra . 2018. Deep learning for entity matching: A design space exploration . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 19 -- 34 . ACM. 200, 201, 202 S. Mudgal, H. Li, T. Rekatsinas, A. Doan, Y. Park, G. Krishnan, R. Deep, E. Arcaute, and V. Raghavendra. 2018. Deep learning for entity matching: A design space exploration. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 19--34. ACM. 200, 201, 202"},{"key":"e_1_4_1_179_1","first-page":"39","article-title":"Outrank: ranking outliers in high dimensional data. In Proceedings of the Workshops of 24th International Conference on Data Engineering, pp. 600--603","volume":"33","author":"Muller E.","year":"2008","unstructured":"E. Muller , I. Assent , U. Steinhausen , and T. Seidl . 2008 . Outrank: ranking outliers in high dimensional data. In Proceedings of the Workshops of 24th International Conference on Data Engineering, pp. 600--603 . IEEE. 33 , 37, 39 E. Muller, I. Assent, U. Steinhausen, and T. Seidl. 2008. Outrank: ranking outliers in high dimensional data. In Proceedings of the Workshops of 24th International Conference on Data Engineering, pp. 600--603. IEEE. 33, 37, 39","journal-title":"IEEE."},{"key":"e_1_4_1_180_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00262ED1V01Y201003DTM003"},{"key":"e_1_4_1_181_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-010-9156-z"},{"key":"e_1_4_1_182_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.130.3381.954"},{"key":"e_1_4_1_183_1","first-page":"104","volume-title":"Proceedings of the 40th Annual Meeting Assoc. for Computational Linguistics","author":"Ng V.","unstructured":"V. Ng and C. Cardie . 2002. Improving machine learning approaches to coreference resolution . In Proceedings of the 40th Annual Meeting Assoc. for Computational Linguistics , pp. 104 -- 111 . 60 V. Ng and C. Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting Assoc. for Computational Linguistics, pp. 104--111. 60"},{"key":"e_1_4_1_184_1","first-page":"949","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Okcan A.","unstructured":"A. Okcan and M. Riedewald . 2011. Processing theta-joins using mapReduce . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 949 -- 960 . ACM. 68 A. Okcan and M. Riedewald. 2011. Processing theta-joins using mapReduce. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 949--960. ACM. 68"},{"key":"e_1_4_1_185_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.54"},{"key":"e_1_4_1_186_1","doi-asserted-by":"publisher","DOI":"10.14778\/2947618.2947624"},{"key":"e_1_4_1_187_1","first-page":"315","volume-title":"Proceedings of the 19th International Conference on Data Engineering","author":"Papadimitriou S.","unstructured":"S. Papadimitriou , H. Kitagawa , P. B. Gibbons , and C. Faloutsos . 2003. LOCI: fast outlier detection using the local correlation integral . In Proceedings of the 19th International Conference on Data Engineering , pp. 315 -- 326 . 30 S. Papadimitriou, H. Kitagawa, P. B. Gibbons, and C. Faloutsos. 2003. LOCI: fast outlier detection using the local correlation integral. In Proceedings of the 19th International Conference on Data Engineering, pp. 315--326. 30"},{"key":"e_1_4_1_188_1","first-page":"821","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Papenbrock T.","unstructured":"T. Papenbrock and F. Naumann . 2016. A hybrid approach to functional dependency discovery . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 821 -- 833 . ACM. 128, 130, 148 T. Papenbrock and F. Naumann. 2016. A hybrid approach to functional dependency discovery. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 821--833. ACM. 128, 130, 148"},{"key":"e_1_4_1_189_1","doi-asserted-by":"publisher","DOI":"10.14778\/2794367.2794377"},{"key":"e_1_4_1_190_1","doi-asserted-by":"publisher","DOI":"10.14778\/2752939.2752946"},{"key":"e_1_4_1_191_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007731"},{"key":"e_1_4_1_192_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"e_1_4_1_193_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1894.0003"},{"key":"e_1_4_1_194_1","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"issue":"12","key":"e_1_4_1_195_1","first-page":"54","article-title":"Hanging on the metaphone","volume":"7","author":"Philips L.","year":"1990","unstructured":"L. Philips . 1990 . Hanging on the metaphone . Computer Language , 7 ( 12 ). 54 L. Philips. 1990. Hanging on the metaphone. Computer Language, 7(12). 54","journal-title":"Computer Language"},{"key":"e_1_4_1_196_1","unstructured":"L. Philips. 2000. The double metaphone search algorithm. C\/C++ Users Journal 18(6): 38--43. 54  L. Philips. 2000. The double metaphone search algorithm. C\/C ++ Users Journal 18(6): 38--43. 54"},{"key":"e_1_4_1_197_1","first-page":"650","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Poon H.","unstructured":"H. Poon and P. Domingos . 2008. Joint unsupervised coreference resolution with Markov logic . In Proceedings of the Conference on Empirical Methods in Natural Language Processing , pp. 650 -- 659 . Association for Computational Linguistics. 205 H. Poon and P. Domingos. 2008. Joint unsupervised coreference resolution with Markov logic. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 650--659. Association for Computational Linguistics. 205"},{"key":"e_1_4_1_198_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100057"},{"key":"e_1_4_1_199_1","first-page":"2000","article-title":"Data cleaning: Problems and current approaches","volume":"23","author":"Rahm E.","year":"2000","unstructured":"E. Rahm and H. H. Do . 2000 . Data cleaning: Problems and current approaches . IEEE Data Engineering Bulletin , 23 : 2000 . DOI: 10.1.1.98.8661. 2 E. Rahm and H. H. Do. 2000. Data cleaning: Problems and current approaches. IEEE Data Engineering Bulletin, 23:2000. DOI: 10.1.1.98.8661. 2","journal-title":"IEEE Data Engineering Bulletin"},{"key":"e_1_4_1_200_1","first-page":"381","volume-title":"Proceedings of the 27th International Conference on Very Large Data Bases VLDB Endowment","author":"Raman V.","unstructured":"V. Raman and J. M. Hellerstein . 2001. Potter's Wheel: An interactive data cleaning system. In P. M. G. Apers, P. Atzeni, S. Ceri, S. Paraboschi, K. Ramamohanarao, and R. T. Snodgrass, editors , Proceedings of the 27th International Conference on Very Large Data Bases VLDB Endowment , pp. 381 -- 390 . Morgan & Claypool Publishers, San Rafael, CA. 91, 93, 94, 96 V. Raman and J. M. Hellerstein. 2001. Potter's Wheel: An interactive data cleaning system. In P. M. G. Apers, P. Atzeni, S. Ceri, S. Paraboschi, K. Ramamohanarao, and R. T. Snodgrass, editors, Proceedings of the 27th International Conference on Very Large Data Bases VLDB Endowment, pp. 381--390. Morgan & Claypool Publishers, San Rafael, CA. 91, 93, 94, 96"},{"key":"e_1_4_1_201_1","first-page":"427","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Ramaswamy S.","unstructured":"S. Ramaswamy , R. Rastogi , and K. Shim . 2000. Efficient algorithms for mining outliers from large data sets . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 427 -- 438 . 27 S. Ramaswamy, R. Rastogi, and K. Shim. 2000. Efficient algorithms for mining outliers from large data sets. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 427--438. 27"},{"key":"e_1_4_1_202_1","doi-asserted-by":"publisher","DOI":"10.14778\/1938545.1938546"},{"key":"e_1_4_1_203_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_4_1_204_1","unstructured":"A. J. Ratner C. M. De Sa S. Wu D. Selsam and C. R\u00e9. 2016. Data programming: Creating large training sets quickly. In Advances in neural information processing systems pp. 3567--3575. 220 221  A. J. Ratner C. M. De Sa S. Wu D. Selsam and C. R\u00e9. 2016. Data programming: Creating large training sets quickly. In Advances in neural information processing systems pp. 3567--3575. 220 221"},{"key":"e_1_4_1_205_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1033211"},{"key":"e_1_4_1_206_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_4_1_207_1","first-page":"1399","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Rekatsinas T.","unstructured":"T. Rekatsinas , M. Joglekar , H. Garcia-Molina , A. G. Parameswaran , and C. R\u00e9 . 2017b. Slimfast: Guaranteed results for data fusion and source reliability . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 1399 -- 1414 . 196, 205 T. Rekatsinas, M. Joglekar, H. Garcia-Molina, A. G. Parameswaran, and C. R\u00e9. 2017b. Slimfast: Guaranteed results for data fusion and source reliability. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 1399--1414. 196, 205"},{"key":"e_1_4_1_208_1","doi-asserted-by":"crossref","unstructured":"M. Richardson and P. Domingos. February 2006. Markov logic networks. Mach. Learn. 62(1--2): 107--136. 205  M. Richardson and P. Domingos. February 2006. Markov logic networks. Mach. Learn. 62(1--2): 107--136. 205","DOI":"10.1007\/s10994-006-5833-1"},{"key":"e_1_4_1_209_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728190"},{"key":"e_1_4_1_210_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1983.10487848"},{"key":"e_1_4_1_211_1","doi-asserted-by":"publisher","DOI":"10.2307\/1270566"},{"key":"e_1_4_1_212_1","unstructured":"R. C. Russell. 1918. Index April 2 1918. URL http:\/\/www.google.com\/patents\/US1261167. U.S. Patent 1 261 167. 53  R. C. Russell. 1918. Index April 2 1918. URL http:\/\/www.google.com\/patents\/US1261167. U.S. Patent 1 261 167. 53"},{"key":"e_1_4_1_213_1","first-page":"3097","volume-title":"Advances in Neural Information Proc. Systems 28, Proc. 29th Annual Conf. on Neural Information Proc. Systems","author":"Sa C. De","unstructured":"C. De Sa , C. Zhang , K. Olukotun , and C. R\u00e9 . 2015. Rapidly mixing Gibbs sampling for a class of factor graphs using hierarchy width . In Advances in Neural Information Proc. Systems 28, Proc. 29th Annual Conf. on Neural Information Proc. Systems , pp. 3097 -- 3105 . 211 C. De Sa, C. Zhang, K. Olukotun, and C. R\u00e9. 2015. Rapidly mixing Gibbs sampling for a class of factor graphs using hierarchy width. In Advances in Neural Information Proc. Systems 28, Proc. 29th Annual Conf. on Neural Information Proc. Systems, pp. 3097--3105. 211"},{"key":"e_1_4_1_214_1","first-page":"306","volume-title":"FLAIRS Conference","author":"Salvador S.","unstructured":"S. Salvador , P. Chan , and J. Brodie . 2004. Learning states and rules for time series anomaly detection . In FLAIRS Conference , pp. 306 -- 311 . 40 S. Salvador, P. Chan, and J. Brodie. 2004. Learning states and rules for time series anomaly detection. In FLAIRS Conference, pp. 306--311. 40"},{"key":"e_1_4_1_215_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000003"},{"key":"e_1_4_1_216_1","first-page":"269","volume-title":"Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Sarawagi S.","unstructured":"S. Sarawagi and A. Bhamidipaty . 2002. Interactive deduplication using active learning . In Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pp. 269 -- 278 . 195, 196, 197, 198, 200 S. Sarawagi and A. Bhamidipaty. 2002. Interactive deduplication using active learning. In Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 269--278. 195, 196, 197, 198, 200"},{"key":"e_1_4_1_217_1","first-page":"1055","volume-title":"Proceedings of the 21st ACM International Conference on Information and Knowledge Management","author":"Sarma A.-D.","unstructured":"A.-D. Sarma , A. Jain , A. Machanavajjhala , and P. Bohannon . 2012. An automatic blocking mechanism for large-scale de-duplication tasks . In Proceedings of the 21st ACM International Conference on Information and Knowledge Management , pp. 1055 -- 1064 . 62 A.-D. Sarma, A. Jain, A. Machanavajjhala, and P. Bohannon. 2012. An automatic blocking mechanism for large-scale de-duplication tasks. In Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp. 1055--1064. 62"},{"key":"e_1_4_1_218_1","first-page":"839","volume-title":"Proceedings of the 17th International Conference on Machine Learning","author":"Schohn G.","unstructured":"G. Schohn and D. Cohn . 2000. Less is more: Active learning with support vector machines . In Proceedings of the 17th International Conference on Machine Learning , pp. 839 -- 846 . 199 G. Schohn and D. Cohn. 2000. Less is more: Active learning with support vector machines. In Proceedings of the 17th International Conference on Machine Learning, pp. 839--846. 199"},{"key":"e_1_4_1_219_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"e_1_4_1_220_1","first-page":"195","volume-title":"Multivariate Density Estimation: Theory, Practice, and Visualization","author":"Scott D. W.","unstructured":"D. W. Scott . 2008. The curse of dimensionality and dimension reduction . In Multivariate Density Estimation: Theory, Practice, and Visualization , pp. 195 -- 217 . 12, 32 D. W. Scott. 2008. The curse of dimensionality and dimension reduction. In Multivariate Density Estimation: Theory, Practice, and Visualization, pp. 195--217. 12, 32"},{"key":"e_1_4_1_221_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-009-0153-2"},{"key":"e_1_4_1_222_1","first-page":"371","volume-title":"Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Shekhar S.","unstructured":"S. Shekhar , C.-T. Lu , and P. Zhang . 2001. Detecting graph-based spatial outliers: algorithms and applications (a summary of results) . In Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pp. 371 -- 376 . ACM. 40 S. Shekhar, C.-T. Lu, and P. Zhang. 2001. Detecting graph-based spatial outliers: algorithms and applications (a summary of results). In Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 371--376. ACM. 40"},{"key":"e_1_4_1_223_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809991"},{"key":"e_1_4_1_224_1","unstructured":"J. Shlens. 2014. A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100. 33  J. Shlens. 2014. A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100. 33"},{"key":"e_1_4_1_225_1","volume-title":"Smoothing methods in statistics","author":"Simonoff J. S.","unstructured":"J. S. Simonoff . 2012. Smoothing methods in statistics . Springer Science +Business Media. 25 J. S. Simonoff. 2012. Smoothing methods in statistics. Springer Science+Business Media. 25"},{"key":"e_1_4_1_226_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1951.tb00088.x"},{"key":"e_1_4_1_227_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212356"},{"key":"e_1_4_1_228_1","first-page":"572","volume-title":"Proceedings of the 2006 IEEE International Conference on Data Mining","author":"Singla P.","unstructured":"P. Singla and P. Domingos . 2006. Entity resolution with Markov logic . In Proceedings of the 2006 IEEE International Conference on Data Mining , pp. 572 -- 582 . 205 P. Singla and P. Domingos. 2006. Entity resolution with Markov logic. In Proceedings of the 2006 IEEE International Conference on Data Mining, pp. 572--582. 205"},{"key":"e_1_4_1_229_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.807277"},{"key":"e_1_4_1_230_1","first-page":"1421","volume-title":"Proceedings of the 18th ACM International Conference on Information and Knowledge Management","author":"Song S.","unstructured":"S. Song and L. Chen . 2009. Discovering matching dependencies . In Proceedings of the 18th ACM International Conference on Information and Knowledge Management , pp. 1421 -- 1424 . 141 S. Song and L. Chen. 2009. Discovering matching dependencies. In Proceedings of the 18th ACM International Conference on Information and Knowledge Management, pp. 1421--1424. 141"},{"key":"e_1_4_1_231_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.1009"},{"key":"e_1_4_1_232_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120101753342653"},{"key":"e_1_4_1_233_1","unstructured":"B. W. Steuart and Precision Indexing Staff. 1994. The Daitch-Mokotoff Soundex Reference Guide. Heritage Quest. 54  B. W. Steuart and Precision Indexing Staff. 1994. The Daitch-Mokotoff Soundex Reference Guide. Heritage Quest. 54"},{"issue":"2","key":"e_1_4_1_234_1","first-page":"3","article-title":"Data integration: The current status and the way forward","volume":"41","author":"Stonebraker M.","year":"2018","unstructured":"M. Stonebraker and I. F. Ilyas . 2018 . Data integration: The current status and the way forward . IEEE Data Eng. Bull. , 41 ( 2 ): 3 -- 9 . 196 M. Stonebraker and I. F. Ilyas. 2018. Data integration: The current status and the way forward. IEEE Data Eng. Bull., 41(2): 3--9. 196","journal-title":"IEEE Data Eng. Bull."},{"issue":"1","key":"e_1_4_1_235_1","first-page":"1","article-title":"Data curation at scale: The data tamer system. In Proceedings of the 6th Biennial Conf. on Innovative Data Systems Research","volume":"10","author":"Stonebraker M.","year":"2013","unstructured":"M. Stonebraker , D. Bruckner , I. F. Ilyas , G. Beskales , M. Cherniack , S. B. Zdonik , A. Pagan , and S. Xu . 2013 . Data curation at scale: The data tamer system. In Proceedings of the 6th Biennial Conf. on Innovative Data Systems Research . DOI : 10 . 1 . 1 .302.8817. 6, 85, 87, 163, 197 M. Stonebraker, D. Bruckner, I. F. Ilyas, G. Beskales, M. Cherniack, S. B. Zdonik, A. Pagan, and S. Xu. 2013. Data curation at scale: The data tamer system. In Proceedings of the 6th Biennial Conf. on Innovative Data Systems Research. DOI: 10.1.1.302.8817. 6, 85, 87, 163, 197","journal-title":"DOI"},{"key":"e_1_4_1_236_1","volume-title":"Drop: Dimensionality reduction optimization for time series. arXiv preprint arXiv:1708.00183. 33","author":"Suri S.","year":"2017","unstructured":"S. Suri and P. Bailis . 2017 . Drop: Dimensionality reduction optimization for time series. arXiv preprint arXiv:1708.00183. 33 S. Suri and P. Bailis. 2017. Drop: Dimensionality reduction optimization for time series. arXiv preprint arXiv:1708.00183. 33"},{"key":"e_1_4_1_237_1","volume-title":"Name Search Techniques. Special report (New York State Identification and Intelligence System)","author":"Taft R. L.","unstructured":"R. L. Taft . 1970. Name Search Techniques. Special report (New York State Identification and Intelligence System) . Bureau of Systems Development , New York State Identification and Intelligence System. 54 R. L. Taft. 1970. Name Search Techniques. Special report (New York State Identification and Intelligence System). Bureau of Systems Development, New York State Identification and Intelligence System. 54"},{"key":"e_1_4_1_238_1","first-page":"1","volume-title":"Proceedings of the 25th International Conference on Scientific and Statistical Database Management","author":"Tang G.","unstructured":"G. Tang , J. Bailey , J. Pei , and G. Dong . 2013. Mining multidimensional contextual outliers from categorical relational data . In Proceedings of the 25th International Conference on Scientific and Statistical Database Management , pp. 43: 1 -- 43 :4. 33, 40, 41, 43 G. Tang, J. Bailey, J. Pei, and G. Dong. 2013. Mining multidimensional contextual outliers from categorical relational data. In Proceedings of the 25th International Conference on Scientific and Statistical Database Management, pp. 43:1--43:4. 33, 40, 41, 43"},{"key":"e_1_4_1_239_1","first-page":"535","volume-title":"6th Pacific-Asia Conf.","author":"Tang J.","unstructured":"J. Tang , Z. Chen , A. Wai-Chee Fu , and D. Wai-Lok Cheung . 2002. Enhancing effectiveness of outlier detections for low density patterns. In Advances in Knowledge Discovery and Data Mining , 6th Pacific-Asia Conf. , pp. 535 -- 548 . 30 J. Tang, Z. Chen, A. Wai-Chee Fu, and D. Wai-Lok Cheung. 2002. Enhancing effectiveness of outlier detections for low density patterns. In Advances in Knowledge Discovery and Data Mining, 6th Pacific-Asia Conf., pp. 535--548. 30"},{"key":"e_1_4_1_240_1","first-page":"731","volume-title":"13th International Congress on Condition Monitoring and Diagnostic Engineering Management","author":"Taylor O.","unstructured":"O. Taylor and D. Addison . 2000. Novelty detection using neural network technology . In 13th International Congress on Condition Monitoring and Diagnostic Engineering Management , pp. 731 -- 743 . 32 O. Taylor and D. Addison. 2000. Novelty detection using neural network technology. In 13th International Congress on Condition Monitoring and Diagnostic Engineering Management, pp. 731--743. 32"},{"key":"e_1_4_1_241_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4379(01)00042-4"},{"key":"e_1_4_1_242_1","doi-asserted-by":"publisher","DOI":"10.1093\/jmammal\/gyy089"},{"key":"e_1_4_1_243_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1972.10488948"},{"key":"e_1_4_1_244_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244302760185243"},{"key":"e_1_4_1_246_1","first-page":"307","volume-title":"Logics for databases and information systems","author":"van der Meyden R.","unstructured":"R. van der Meyden . 1998. Logical approaches to incomplete information: A survey . In Logics for databases and information systems , pp. 307 -- 356 . Springer . 116 R. van der Meyden. 1998. Logical approaches to incomplete information: A survey. In Logics for databases and information systems, pp. 307--356. Springer. 116"},{"key":"e_1_4_1_247_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0255(00)00013-X"},{"key":"e_1_4_1_248_1","first-page":"244","volume-title":"Proceedings of the 30th International Conference on Data Engineering","author":"Volkovs M.","unstructured":"M. Volkovs , F. Chiang , J. Szlichta , and R. J. Miller . 2014. Continuous data cleaning . In Proceedings of the 30th International Conference on Data Engineering , pp. 244 -- 255 . 164, 173, 174, 177, 178 M. Volkovs, F. Chiang, J. Szlichta, and R. J. Miller. 2014. Continuous data cleaning. In Proceedings of the 30th International Conference on Data Engineering, pp. 244--255. 164, 173, 174, 177, 178"},{"key":"e_1_4_1_249_1","first-page":"457","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Wang J.","unstructured":"J. Wang and N. Tang . 2014. Towards dependable data repairing with fixing rules . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 457 -- 468 . ACM. 139, 144, 145 J. Wang and N. Tang. 2014. Towards dependable data repairing with fixing rules. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 457--468. ACM. 139, 144, 145"},{"key":"e_1_4_1_250_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350263"},{"key":"e_1_4_1_251_1","first-page":"66","article-title":"Can we beat the prefix filtering?: an adaptive framework for similarity join and search. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 85--96","volume":"64","author":"Wang J.","year":"2012","unstructured":"J. Wang , G. Li , and J. Feng . 2012 b. Can we beat the prefix filtering?: an adaptive framework for similarity join and search. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 85--96 . ACM. 64 , 66 J. Wang, G. Li, and J. Feng. 2012b. Can we beat the prefix filtering?: an adaptive framework for similarity join and search. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 85--96. ACM. 64, 66","journal-title":"ACM."},{"key":"e_1_4_1_252_1","first-page":"469","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Wang J.","unstructured":"J. Wang , S. Krishnan , M. J. Franklin , K. Goldberg , T. Kraska , and T. Milo . 2014. A sample-and-clean framework for fast and accurate query processing on dirty data . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 469 -- 480 . 214, 215, 216, 221 J. Wang, S. Krishnan, M. J. Franklin, K. Goldberg, T. Kraska, and T. Milo. 2014. A sample-and-clean framework for fast and accurate query processing on dirty data. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 469--480. 214, 215, 216, 221"},{"key":"e_1_4_1_253_1","doi-asserted-by":"publisher","DOI":"10.1016\/0001-8708(76)90202-4"},{"key":"e_1_4_1_254_1","first-page":"399","volume-title":"7th Pacific-Asia Conf.","author":"Wei L.","unstructured":"L. Wei , W. Qian , A. Zhou , W. Jin , and X. Y. Jeffrey . 2003. HOT: Hypergraph-based outlier test for categorical data. In Advances in Knowledge Discovery and Data Mining , 7th Pacific-Asia Conf. , pp. 399 -- 410 . Springer. 33, 40, 41, 43 L. Wei, W. Qian, A. Zhou, W. Jin, and X. Y. Jeffrey. 2003. HOT: Hypergraph-based outlier test for categorical data. In Advances in Knowledge Discovery and Data Mining, 7th Pacific-Asia Conf., pp. 399--410. Springer. 33, 40, 41, 43"},{"key":"e_1_4_1_255_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065795000251"},{"key":"e_1_4_1_256_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454165"},{"key":"e_1_4_1_257_1","unstructured":"P. Wessa. 2012. Free Statistics Software Office for Research Development and Education version 1.2.2. 23-r7. http:\/\/www.wessa.net. 24 26  P. Wessa. 2012. Free Statistics Software Office for Research Development and Education version 1.2.2. 23-r7. http:\/\/www.wessa.net. 24 26"},{"key":"e_1_4_1_258_1","first-page":"52","article-title":"String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage","volume":"51","author":"Winkler W. E.","year":"1990","unstructured":"W. E. Winkler . 1990 . String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage . Proceedings of the Section on Survey Research. 51 , 52 W. E. Winkler. 1990. String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. Proceedings of the Section on Survey Research. 51, 52","journal-title":"Proceedings of the Section on Survey Research."},{"key":"e_1_4_1_259_1","first-page":"56","article-title":"Improved decision rules in the Fellegi-Sunter model of record linkage","volume":"1993","author":"Winkler W. E.","year":"1993","unstructured":"W. E. Winkler . 1993 . Improved decision rules in the Fellegi-Sunter model of record linkage . Bureau of the Census , 1993. 56 W. E. Winkler. 1993. Improved decision rules in the Fellegi-Sunter model of record linkage. Bureau of the Census, 1993. 56","journal-title":"Bureau of the Census"},{"key":"e_1_4_1_260_1","volume-title":"Statistical Research Division","author":"Winkler W. E.","unstructured":"W. E. Winkler . 1999. The state of record linkage and current research problems . In Statistical Research Division , U.S. Census Bureau . 55 W. E. Winkler. 1999. The state of record linkage and current research problems. In Statistical Research Division, U.S. Census Bureau. 55"},{"key":"e_1_4_1_261_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536354.2536356"},{"key":"e_1_4_1_262_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367531"},{"key":"e_1_4_1_263_1","first-page":"101","volume-title":"International Conference on BigData Analytics and Knowledge Discovery","author":"Wyss C. M.","unstructured":"C. M. Wyss , C. Giannella , and E. L. Robertson . 2001. FastFDs: A heuristic-driven, depth-first algorithm for mining functional dependencies from relation instances . In International Conference on BigData Analytics and Knowledge Discovery , pp. 101 -- 110 . 125, 127, 148 C. M. Wyss, C. Giannella, and E. L. Robertson. 2001. FastFDs: A heuristic-driven, depth-first algorithm for mining functional dependencies from relation instances. In International Conference on BigData Analytics and Knowledge Discovery, pp. 101--110. 125, 127, 148"},{"key":"e_1_4_1_264_1","doi-asserted-by":"publisher","DOI":"10.14778\/1952376.1952378"},{"key":"e_1_4_1_265_1","first-page":"553","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data","author":"Yakout M.","unstructured":"M. Yakout , L. Berti-\u00c9quille , and A. K. Elmagarmid . 2013. Don't be scared: use scalable automatic repairing with maximal likelihood and bounded changes . In Proceedings of the ACM SIGMOD International Conference on Management of Data , pp. 553 -- 564 . 208 M. Yakout, L. Berti-\u00c9quille, and A. K. Elmagarmid. 2013. Don't be scared: use scalable automatic repairing with maximal likelihood and bounded changes. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 553--564. 208"},{"key":"e_1_4_1_266_1","first-page":"1283","volume-title":"Proceedings of the VLDB Endowment","author":"Zhang C.","unstructured":"C. Zhang and C. R\u00e9 . 2014. Dimmwitted: A study of main-memory statistical analytics . Proceedings of the VLDB Endowment , pp. 1283 -- 1294 . 210 C. Zhang and C. R\u00e9. 2014. Dimmwitted: A study of main-memory statistical analytics. Proceedings of the VLDB Endowment, pp. 1283--1294. 210"},{"key":"e_1_4_1_267_1","first-page":"1265","volume-title":"Proceedings of the 30th International Conference on Very Large Data Bases","author":"Zhang J.","unstructured":"J. Zhang , M. Lou , T. W. Ling , and H. Wang . 2004. HOS-miner: a system for detecting outlyting subspaces of high-dimensional data . In Proceedings of the 30th International Conference on Very Large Data Bases , pp. 1265 -- 1268 . 33, 37, 39, 40 J. Zhang, M. Lou, T. W. Ling, and H. Wang. 2004. HOS-miner: a system for detecting outlyting subspaces of high-dimensional data. In Proceedings of the 30th International Conference on Very Large Data Bases, pp. 1265--1268. 33, 37, 39, 40"},{"key":"e_1_4_1_268_1","first-page":"222","volume-title":"8th Pacific-Asia Conf.","author":"Zhu C.","unstructured":"C. Zhu , H. Kitagawa , S. Papadimitriou , and C. Faloutsos . 2004. OBE: outlier by example. In Advances in Knowledge Discovery and Data Mining , 8th Pacific-Asia Conf. , pp. 222 -- 234 . Springer. 33, 40 C. Zhu, H. Kitagawa, S. Papadimitriou, and C. Faloutsos. 2004. OBE: outlier by example. In Advances in Knowledge Discovery and Data Mining, 8th Pacific-Asia Conf., pp. 222--234. Springer. 33, 40"},{"key":"e_1_4_1_269_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-004-0751-8"}],"container-title":[],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3310205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T10:22:03Z","timestamp":1672914123000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/book\/10.1145\/3310205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,9]]},"ISBN":["9781450371520"],"references-count":268,"alternative-id":["10.1145\/3310205"],"URL":"https:\/\/doi.org\/10.1145\/3310205","relation":{},"subject":[],"published":{"date-parts":[[2019,7,9]]},"assertion":[{"value":"2019-07-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}