{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:32:00Z","timestamp":1765546320261,"version":"3.37.3"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,5,17]],"date-time":"2018-05-17T00:00:00Z","timestamp":1526515200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"973 Program","doi-asserted-by":"crossref","award":["2015CB358700"],"award-info":[{"award-number":["2015CB358700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61632016","61373024"],"award-info":[{"award-number":["61632016","61373024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602488","61422205"],"award-info":[{"award-number":["61602488","61422205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472198"],"award-info":[{"award-number":["61472198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s00778-018-0506-9","type":"journal-article","created":{"date-parts":[[2018,5,16]],"date-time":"2018-05-16T22:09:56Z","timestamp":1526508596000},"page":"497-519","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Distilling relations using knowledge bases"],"prefix":"10.1007","volume":"27","author":[{"given":"Shuang","family":"Hao","sequence":"first","affiliation":[]},{"given":"Nan","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,5,17]]},"reference":[{"issue":"12","key":"506_CR1","first-page":"993","volume":"9","author":"Z Abedjan","year":"2016","unstructured":"Abedjan, Z., Chu, X., Deng, D., Fernandez, R.C., Ilyas, I.F., Ouzzani, M., Papotti, P., Stonebraker, M., Tang, N.: Detecting data errors: where are we and what needs to be done? PVLDB 9(12), 993\u20131004 (2016)","journal-title":"PVLDB"},{"key":"506_CR2","volume-title":"Foundations of Databases","author":"S Abiteboul","year":"1995","unstructured":"Abiteboul, S., Hull, R., Vianu, V.: Foundations of Databases. Addison-Wesley, Boston (1995)"},{"key":"506_CR3","doi-asserted-by":"crossref","unstructured":"Anchuri, P., Zaki, M.J., Barkol, O., Golan, S., Shamy, M.: Approximate graph mining with label costs. In: KDD, pp. 518\u2013526 (2013)","DOI":"10.1145\/2487575.2487602"},{"key":"506_CR4","doi-asserted-by":"crossref","unstructured":"Arenas, M., Bertossi, L.E., Chomicki, J.: Consistent query answers in inconsistent databases. In: SIGMOD, pp. 68\u201379. ACM (1999)","DOI":"10.1145\/303976.303983"},{"key":"506_CR5","unstructured":"Bach, S.H., Broecheler, M., Huang, B., Getoor, L.: Hinge-loss markov random fields and probabilistic soft logic. CoRR, \n                    arXiv:1505.04406\n                    \n                   (2015)"},{"issue":"1","key":"506_CR6","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00778-008-0098-x","volume":"18","author":"O Benjelloun","year":"2009","unstructured":"Benjelloun, O., Garcia-Molina, H., Menestrina, D., Su, Q., Whang, S.E., Widom, J.: Swoosh: a generic approach to entity resolution. VLDB J. 18(1), 255\u2013276 (2009)","journal-title":"VLDB J."},{"key":"506_CR7","doi-asserted-by":"crossref","unstructured":"Bohannon, P., Fan, W., Flaster, M., Rastogi, R.: A cost-based model and effective heuristic for repairing constraints by value modification. In: SIGMOD (2005)","DOI":"10.1145\/1066157.1066175"},{"key":"506_CR8","doi-asserted-by":"crossref","unstructured":"Chai, C., Li, G., Li, J., Deng, D., Feng, J.: Cost-effective crowdsourced entity resolution: a partial-order approach. In: SIGMOD, pp. 969\u2013984 (2016)","DOI":"10.1145\/2882903.2915252"},{"key":"506_CR9","doi-asserted-by":"crossref","unstructured":"Chiang, F., Miller, R.J.: A unified model for data and constraint repair. In: ICDE (2011)","DOI":"10.1109\/ICDE.2011.5767833"},{"key":"506_CR10","unstructured":"Chu, X., Ilyas, I.F., Papotti, P.: Holistic data cleaning: putting violations into context. In: ICDE (2013)"},{"key":"506_CR11","doi-asserted-by":"crossref","unstructured":"Chu, X., Morcos, J., Ilyas, I.F., Ouzzani, M., Papotti, P., Tang, N., Ye, Y.: KATARA: a data cleaning system powered by knowledge bases and crowdsourcing. In: SIGMOD (2015)","DOI":"10.1145\/2723372.2749431"},{"key":"506_CR12","unstructured":"Cong, G., Fan, W., Geerts, F., Jia, X., Ma, S.: Improving data quality: consistency and accuracy. In: VLDB (2007)"},{"key":"506_CR13","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., Ebaid, A., Eldawy, A., Elmagarmid, A.K., Ilyas, I.F., Ouzzani, M., Tang, N.: NADEEF: a commodity data cleaning system. In: SIGMOD (2013)","DOI":"10.1145\/2463676.2465327"},{"issue":"13","key":"506_CR14","first-page":"1606","volume":"6","author":"D Deng","year":"2013","unstructured":"Deng, D., Jiang, Y., Li, G., Li, J., Yu, C.: Scalable column concept determination for web tables using large knowledge bases. PVLDB 6(13), 1606\u20131617 (2013)","journal-title":"PVLDB"},{"issue":"4","key":"506_CR15","first-page":"360","volume":"9","author":"D Deng","year":"2015","unstructured":"Deng, D., Li, G., Wen, H., Feng, J.: An efficient partition based method for exact set similarity joins. PVLDB 9(4), 360\u2013371 (2015)","journal-title":"PVLDB"},{"key":"506_CR16","doi-asserted-by":"crossref","unstructured":"Deshpande, O., Lamba, D.S., Tourn, M., Das, S., Subramaniam, S., Rajaraman, A., Harinarayan, V., Doan, A.: Building, maintaining, and using knowledge bases: a report from the trenches. In: SIGMOD Conference (2013)","DOI":"10.1145\/2463676.2465297"},{"key":"506_CR17","doi-asserted-by":"crossref","unstructured":"Dong, X., Gabrilovich, E., Heitz, G., Horn, W., Lao, N., Murphy, K., Strohmann, T., Sun, S., Zhang, W.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: SIGKDD (2014)","DOI":"10.1145\/2623330.2623623"},{"issue":"10","key":"506_CR18","first-page":"881","volume":"7","author":"XL Dong","year":"2014","unstructured":"Dong, X.L., Gabrilovich, E., Heitz, G., Horn, W., Murphy, K., Sun, S., Zhang, W.: From data fusion to knowledge fusion. PVLDB 7(10), 881\u2013892 (2014)","journal-title":"PVLDB"},{"key":"506_CR19","doi-asserted-by":"crossref","unstructured":"Fan, W.: Dependencies revisited for improving data quality. In: PODS (2008)","DOI":"10.1145\/1376916.1376940"},{"issue":"12","key":"506_CR20","first-page":"1590","volume":"8","author":"W Fan","year":"2015","unstructured":"Fan, W., Fan, Z., Tian, C., Dong, X.L.: Keys for graphs. PVLDB 8(12), 1590\u20131601 (2015)","journal-title":"Keys for graphs. PVLDB"},{"issue":"2","key":"506_CR21","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1145\/1366102.1366103","volume":"33","author":"W Fan","year":"2008","unstructured":"Fan, W., Geerts, F., Jia, X., Kementsietsidis, A.: Conditional functional dependencies for capturing data inconsistencies. TODS 33(2), 6 (2008)","journal-title":"TODS"},{"issue":"1","key":"506_CR22","first-page":"407","volume":"2","author":"W Fan","year":"2009","unstructured":"Fan, W., Jia, X., Li, J., Ma, S.: Reasoning about record matching rules. PVLDB 2(1), 407\u2013418 (2009)","journal-title":"Reasoning about record matching rules. PVLDB"},{"issue":"2","key":"506_CR23","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s00778-011-0253-7","volume":"21","author":"W Fan","year":"2012","unstructured":"Fan, W., Li, J., Ma, S., Tang, N., Yu, W.: Towards certain fixes with editing rules and master data. VLDB J. 21(2), 213\u2013238 (2012)","journal-title":"VLDB J."},{"issue":"4","key":"506_CR24","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s00778-011-0252-8","volume":"21","author":"J Feng","year":"2012","unstructured":"Feng, J., Wang, J., Li, G.: Trie-join: a trie-based method for efficient string similarity joins. VLDB J. 21(4), 437\u2013461 (2012)","journal-title":"VLDB J."},{"issue":"9","key":"506_CR25","first-page":"625","volume":"6","author":"F Geerts","year":"2013","unstructured":"Geerts, F., Mecca, G., Papotti, P., Santoro, D.: The LLUNATIC data-cleaning framework. PVLDB 6(9), 625\u2013636 (2013)","journal-title":"The LLUNATIC data-cleaning framework. PVLDB"},{"key":"506_CR26","doi-asserted-by":"crossref","unstructured":"Hao, S., Tang, N., Li, G., Li, J.: Cleaning relations using knowledge bases. In: ICDE (2017)","DOI":"10.1109\/ICDE.2017.141"},{"key":"506_CR27","doi-asserted-by":"crossref","unstructured":"He, J., Veltri, E., Santoro, D., Li, G., Mecca, G., Papotti, P., Tang, N.: Interactive and deterministic data cleaning. In: SIGMOD (2016)","DOI":"10.1145\/2882903.2915242"},{"key":"506_CR28","unstructured":"Heer, J., Hellerstein, J.M., Kandel, S.: Predictive interaction for data transformation. In: CIDR (2015)"},{"key":"506_CR29","volume-title":"Data Quality and Record Linkage Techniques","author":"TN Herzog","year":"2009","unstructured":"Herzog, T.N., Scheuren, F.J., Winkler, W.E.: Data Quality and Record Linkage Techniques. Springer, Berlin (2009)"},{"key":"506_CR30","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.artint.2012.06.001","volume":"194","author":"J Hoffart","year":"2013","unstructured":"Hoffart, J., Suchanek, F.M., Berberich, K., Weikum, G.: YAGO2: A spatially and temporally enhanced knowledge base from wikipedia. Artif. Intell. 194, 28\u201361 (2013)","journal-title":"Artif. Intell."},{"key":"506_CR31","doi-asserted-by":"crossref","unstructured":"Interlandi, M., Tang, N.: Proof positive and negative in data cleaning. In: ICDE (2015)","DOI":"10.1109\/ICDE.2015.7113269"},{"issue":"8","key":"506_CR32","first-page":"625","volume":"7","author":"Y Jiang","year":"2014","unstructured":"Jiang, Y., Li, G., Feng, J., Li, W.: String similarity joins: an experimental evaluation. PVLDB 7(8), 625\u2013636 (2014)","journal-title":"PVLDB"},{"key":"506_CR33","doi-asserted-by":"crossref","unstructured":"Khayyat, Z., Ilyas, I.F., Jindal, A., Madden, S., Ouzzani, M., Papotti, P., Quian\u00e9-Ruiz, J.-A., Tang, N., Yin, S.: Bigdansing: a system for big data cleansing. In: SIGMOD (2015)","DOI":"10.1145\/2723372.2747646"},{"key":"506_CR34","doi-asserted-by":"crossref","unstructured":"Li, G.: A human-machine method for web table understanding. In: WAIM, pp. 179\u2013189 (2013)","DOI":"10.1007\/978-3-642-38562-9_19"},{"issue":"12","key":"506_CR35","first-page":"2006","volume":"10","author":"G Li","year":"2017","unstructured":"Li, G.: Human-in-the-loop data integration. PVLDB 10(12), 2006\u20132017 (2017)","journal-title":"PVLDB"},{"key":"506_CR36","doi-asserted-by":"crossref","unstructured":"Li, G., Chai, C., Fan, J., Weng, X., Li, J., Zheng, Y., Li, Y., Yu, X., Zhang, X., Yuan, H.: CDB: optimizing queries with crowd-based selections and joins. In: SIGMOD, pp. 1463\u20131478 (2017)","DOI":"10.1145\/3035918.3064036"},{"issue":"3","key":"506_CR37","first-page":"253","volume":"5","author":"G Li","year":"2011","unstructured":"Li, G., Deng, D., Wang, J., Feng, J.: PASS-JOIN: a partition-based method for similarity joins. PVLDB 5(3), 253\u2013264 (2011)","journal-title":"PVLDB"},{"key":"506_CR38","doi-asserted-by":"crossref","unstructured":"Li, G., Ooi, B.C., Feng, J., Wang, J., Zhou, L.: EASE: an effective 3-in-1 keyword search method for unstructured, semi-structured and structured data. In: SIGMOD, pp. 903\u2013914 (2008)","DOI":"10.1145\/1376616.1376706"},{"issue":"9","key":"506_CR39","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.1109\/TKDE.2016.2535242","volume":"28","author":"G Li","year":"2016","unstructured":"Li, G., Wang, J., Zheng, Y., Franklin, M.J.: Crowdsourced data management: a survey. IEEE Trans. Knowl. Data Eng. 28(9), 2296\u20132319 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"12","key":"506_CR40","first-page":"1338","volume":"3","author":"G Limaye","year":"2010","unstructured":"Limaye, G., Sarawagi, S., Chakrabarti, S.: Annotating and searching web tables using entities, types and relationships. PVLDB 3(12), 1338\u20131347 (2010)","journal-title":"PVLDB"},{"key":"506_CR41","doi-asserted-by":"crossref","unstructured":"Morsey, M., Lehmann, J., Auer, S., Ngomo, A.N.: Dbpedia SPARQL benchmark\u2014performance assessment with real queries on real data. In: ISWC (2011)","DOI":"10.1007\/978-3-642-25073-6_29"},{"issue":"6","key":"506_CR42","first-page":"373","volume":"4","author":"F Niu","year":"2011","unstructured":"Niu, F., R\u00e9, C., Doan, A., Shavlik, J.W.: Tuffy: Scaling up statistical inference in markov logic networks using an RDBMS. PVLDB 4(6), 373\u2013384 (2011)","journal-title":"PVLDB"},{"key":"506_CR43","unstructured":"Raman, V., Hellerstein, J.M.: Potter\u2019s wheel: an interactive data cleaning system. In: VLDB (2001)"},{"issue":"11","key":"506_CR44","first-page":"1190","volume":"10","author":"T Rekatsinas","year":"2017","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C.: Holoclean Holistic data repairs with probabilistic inference. PVLDB 10(11), 1190\u20131201 (2017)","journal-title":"PVLDB"},{"issue":"12","key":"506_CR45","doi-asserted-by":"publisher","first-page":"3293","DOI":"10.1109\/TKDE.2016.2601325","volume":"28","author":"Z Shang","year":"2016","unstructured":"Shang, Z., Liu, Y., Li, G., Feng, J.: K-join: knowledge-aware similarity join. IEEE Trans. Knowl. Data Eng. 28(12), 3293\u20133308 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"11","key":"506_CR46","first-page":"1310","volume":"8","author":"J Shin","year":"2015","unstructured":"Shin, J., Wu, S., Wang, F., Sa, C.D., Zhang, C., R\u00e9, C.: Incremental knowledge base construction using deepdive. PVLDB 8(11), 1310\u20131321 (2015)","journal-title":"PVLDB"},{"key":"506_CR47","doi-asserted-by":"crossref","unstructured":"Singh, R., Meduri, V., Elmagarmid, A.K., Madden, S., Papotti, P., Quian\u00e9-Ruiz, J., Solar-Lezama, A., Tang, N.: Generating concise entity matching rules. In: PVLDB (2017)","DOI":"10.1145\/3035918.3058739"},{"key":"506_CR48","doi-asserted-by":"crossref","unstructured":"Singh, R., Meduri, V., Elmagarmid, A.K., Madden, S., Papotti, P., Quian\u00e9-Ruiz, J., Solar-Lezama, A., Tang, N.: Synthesizing entity matching rules by examples. In: SIGMOD demo (2017)","DOI":"10.14778\/3149193.3149199"},{"issue":"11","key":"506_CR49","first-page":"987","volume":"7","author":"S Song","year":"2014","unstructured":"Song, S., Cheng, H., Yu, J.X., Chen, L.: Repairing vertex labels under neighborhood constraints. PVLDB 7(11), 987\u2013998 (2014)","journal-title":"PVLDB"},{"issue":"9","key":"506_CR50","first-page":"528","volume":"4","author":"P Venetis","year":"2011","unstructured":"Venetis, P., Halevy, A.Y., Madhavan, J., Pasca, M., Shen, W., Wu, F., Miao, G., Wu, C.: Recovering semantics of tables on the web. PVLDB 4(9), 528\u2013538 (2011)","journal-title":"PVLDB"},{"key":"506_CR51","doi-asserted-by":"crossref","unstructured":"Volkovs, M., Chiang, F., Szlichta, J., Miller, R.J.: Continuous data cleaning. In: ICDE (2014)","DOI":"10.1109\/ICDE.2014.6816655"},{"issue":"1","key":"506_CR52","first-page":"1219","volume":"3","author":"J Wang","year":"2010","unstructured":"Wang, J., Li, G., Feng, J.: Trie-join: efficient trie-based string similarity joins with edit-distance constraints. PVLDB 3(1), 1219\u20131230 (2010)","journal-title":"PVLDB"},{"key":"506_CR53","unstructured":"Wang, J., Li, G., Feng, J.: Fast-join: an efficient method for fuzzy token matching based string similarity join. In: Proceedings of the 27th International Conference on Data Engineering, ICDE 2011, April 11\u201316, 2011, Hannover, Germany, pp. 458\u2013469 (2011)"},{"key":"506_CR54","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, G., Kraska, T., Franklin, M.J., Feng, J.: Leveraging transitive relations for crowdsourced joins. In: SIGMOD, pp. 229\u2013240 (2013)","DOI":"10.1145\/2463676.2465280"},{"key":"506_CR55","doi-asserted-by":"crossref","unstructured":"Wang, J., Tang, N.: Towards dependable data repairing with fixing rules. In: SIGMOD (2014)","DOI":"10.1145\/2588555.2610494"},{"key":"506_CR56","doi-asserted-by":"crossref","unstructured":"Yakout, M., Berti-Equille, L., Elmagarmid, A.K.: Don\u2019t be scared: use scalable automatic repairing with maximal likelihood and bounded changes. In: SIGMOD (2013)","DOI":"10.1145\/2463676.2463706"},{"issue":"5","key":"506_CR57","first-page":"279","volume":"4","author":"M Yakout","year":"2011","unstructured":"Yakout, M., Elmagarmid, A.K., Neville, J., Ouzzani, M., Ilyas, I.F.: Guided data repair. PVLDB 4(5), 279\u2013289 (2011)","journal-title":"Guided data repair. PVLDB"},{"issue":"2","key":"506_CR58","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s00778-016-0449-y","volume":"26","author":"M Yu","year":"2017","unstructured":"Yu, M., Wang, J., Li, G., Zhang, Y., Deng, D., Feng, J.: A unified framework for string similarity search with edit-distance constraint. VLDB J. 26(2), 249\u2013274 (2017)","journal-title":"VLDB J."},{"key":"506_CR59","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Li, G., Feng, Z.Z.J.: Hike: a hybrid human-machine method for entity alignment in large-scale knowledge bases. In: CIKM (2017)","DOI":"10.1145\/3132847.3132912"},{"key":"506_CR60","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Li, G., Zhong, Z., Feng, J.: PBA: partition and blocking based alignment for large knowledge bases. In: DASFAA, pp. 415\u2013431 (2016)","DOI":"10.1007\/978-3-319-32025-0_26"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-018-0506-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-018-0506-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-018-0506-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T19:13:28Z","timestamp":1558034008000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-018-0506-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,17]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["506"],"URL":"https:\/\/doi.org\/10.1007\/s00778-018-0506-9","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2018,5,17]]},"assertion":[{"value":"27 October 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}