{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T13:33:02Z","timestamp":1725975182019},"publisher-location":"Singapore","reference-count":14,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811302916"},{"type":"electronic","value":"9789811302923"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-981-13-0292-3_7","type":"book-chapter","created":{"date-parts":[[2018,4,13]],"date-time":"2018-04-13T14:39:00Z","timestamp":1523630340000},"page":"107-122","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploiting Redundancy, Recurrency and Parallelism: How to Link Millions of Addresses with Ten Lines of Code in Ten Minutes"],"prefix":"10.1007","author":[{"given":"Yuhang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tania","family":"Churchill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kee Siong","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,14]]},"reference":[{"unstructured":"Arasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: Proceedings of the 32nd International Conference on Very Large Data Bases, pp. 918\u2013929. VLDB Endowment (2006)","key":"7_CR1"},{"issue":"8","key":"7_CR2","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1002\/cpa.20124","volume":"59","author":"EJ Cands","year":"2006","unstructured":"Cands, E.J., Romberg, J.K., Tao, T.: Stable signal recovery from incomplete and inaccurate measurements. Commun. Pure Appl. Math. 59(8), 1207\u20131223 (2006)","journal-title":"Commun. Pure Appl. Math."},{"doi-asserted-by":"crossref","unstructured":"Chang, L., Wang, Z., Ma, T., Jian, L., Ma, L., Goldshuv, A., Lonergan, L., Cohen, J., Welton, C., Sherry, G., Bhandarkar, M.: HAWQ: a massively parallel processing SQL engine in Hadoop. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, pp. 1223\u20131234. ACM, New York (2014)","key":"7_CR3","DOI":"10.1145\/2588555.2595636"},{"key":"7_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"unstructured":"Christen, P., Belacic, D.: Automated probabilistic address standardisation and verification. In: Australasian Data Mining Conference (AusDM05) (2005)","key":"7_CR5"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/978-3-540-24775-3_75","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"P Christen","year":"2004","unstructured":"Christen, P., Churches, T., Hegland, M.: Febrl \u2013 a parallel open source data linkage system. In: Dai, H., Srikant, R., Zhang, C. (eds.) PAKDD 2004. LNCS (LNAI), vol. 3056, pp. 638\u2013647. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24775-3_75"},{"unstructured":"Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A comparison of string metrics for matching names and records. In: SIGKDD (2003)","key":"7_CR7"},{"key":"7_CR8","volume-title":"Elasticsearch: The Definitive Guide","author":"C Gormley","year":"2015","unstructured":"Gormley, C., Tong, Z.: Elasticsearch: The Definitive Guide. O\u2019Reilly Media, Sebastopol (2015)"},{"doi-asserted-by":"crossref","unstructured":"Guo, H., Zhu, H., Guo, Z., Zhang, X., Su, Z.: Address standardization with latent semantic association. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2009, pp. 1155\u20131164. ACM, New York (2009)","key":"7_CR9","DOI":"10.1145\/1557019.1557144"},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy, A., Norvig, P., Pereira, F.: The unreasonable effectiveness of data. IEEE Intell. Syst. 24, 8\u201312 (2009)","journal-title":"IEEE Intell. Syst."},{"issue":"12","key":"7_CR11","first-page":"1700","volume":"5","author":"JM Hellerstein","year":"2012","unstructured":"Hellerstein, J.M., R\u00e9, C., Schoppmann, F., Wang, D.Z., Fratkin, E., Gorajek, A., Ng, K.S., Welton, C., Feng, X., Li, K., Kumar, A.: The MADlib analytics library or MAD skills, the SQL. PVLDB 5(12), 1700\u20131711 (2012)","journal-title":"PVLDB"},{"doi-asserted-by":"crossref","unstructured":"Kornacker, M., Behm, A., Bittorf, V., Bobrovytsky, T., Ching, C., Choi, A., Erickson, J., Grund, M., Hecht, D., Jacobs, M., Joshi, I., Kuff, L., Kumar, D., Leblang, A., Li, N., Pandis, I., Robinson, H., Rorke, D., Rus, S., Russell, J., Tsirogiannis, D., Wanderman-Milne, S., Yoder, M.: Impala: a modern, open-source SQL engine for Hadoop. In: CIDR (2015)","key":"7_CR12","DOI":"10.1007\/978-3-658-11589-0_8"},{"unstructured":"Monge, A., Elkan, C.: An efficient domain-independent algorithm for detecting approximately duplicate database records. In: DMKD 1997 (1997)","key":"7_CR13"},{"unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, HotCloud 2010, p. 10. USENIX Association, Berkeley (2010)","key":"7_CR14"}],"container-title":["Communications in Computer and Information Science","Data Mining"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-0292-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T15:57:13Z","timestamp":1571155033000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-13-0292-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9789811302916","9789811302923"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-0292-3_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]}}}