{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T21:08:05Z","timestamp":1760044085929,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,7,23]],"date-time":"2015-07-23T00:00:00Z","timestamp":1437609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s00778-015-0393-2","type":"journal-article","created":{"date-parts":[[2015,7,22]],"date-time":"2015-07-22T10:24:51Z","timestamp":1437560691000},"page":"3-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["epiC: an extensible and scalable system for processing Big Data"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1890-4046","authenticated-orcid":false,"given":"Dawei","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kian-Lee","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,23]]},"reference":[{"key":"393_CR1","doi-asserted-by":"crossref","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Abadi, D., Silberschatz, A., Rasin, A.: Hadoopdb: an architectural hybrid of mapreduce and DBMS technologies for analytical workloads. PVLDB 2(1) (2009)","DOI":"10.14778\/1687627.1687731"},{"key":"393_CR2","doi-asserted-by":"crossref","unstructured":"Battr\u00e9, D., Ewen, S., Hueske, F., Kao, O., Markl, V., Warneke, D.: Nephele\/pacts: a programming model and execution framework for web-scale analytical processing. In: SoCC (2010)","DOI":"10.1145\/1807128.1807148"},{"key":"393_CR3","unstructured":"Bentley, J.L., Sedgewick, R.: Fast algorithms for sorting and searching strings. In: SODA (1997)"},{"key":"393_CR4","doi-asserted-by":"crossref","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.D.: Haloop: efficient iterative data processing on large clusters. VLDB 3(1\u20132), 285\u2013296 (2010)","DOI":"10.14778\/1920841.1920881"},{"key":"393_CR5","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, B., Lin, L., Liu, W., Mittal, S., Aragonda, P., Lychagina, V., Kwon, Y., Wong, M., Wong, M.: Tenzing a SQL implementation on the mapreduce framework (2011)","DOI":"10.14778\/3402755.3402765"},{"key":"393_CR6","doi-asserted-by":"crossref","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","DOI":"10.1145\/1327452.1327492"},{"key":"393_CR7","unstructured":"DeWitt, D.J., Gerber, R.H., Graefe, G., Heytens, M.L., Kumar, K.B., Muralikrishna, M.: Gamma\u2014a high performance dataflow database machine. In: VLDB (1986)"},{"key":"393_CR8","doi-asserted-by":"crossref","unstructured":"DeWitt, D.J., Gray, J.: Parallel database systems: the future of high performance database systems. Commun. ACM 35(6) (1992)","DOI":"10.1145\/129888.129894"},{"key":"393_CR9","doi-asserted-by":"crossref","unstructured":"DeWitt, D.J., Halverson, A., Nehme, R., Shankar, S., Aguilar-Saborit, J., Avanes, A., Flasza, M., Gramling, J.: Split query processing in polybase. In: SIGMOD Conference (2013)","DOI":"10.1145\/2463676.2463709"},{"issue":"4","key":"393_CR10","doi-asserted-by":"crossref","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"},{"key":"393_CR11","doi-asserted-by":"crossref","unstructured":"Finkel, J.R., Grenager, T., Manning, C.D.: Incorporating non-local information into information extraction systems by gibbs sampling. In: ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 25\u201330 June 2005, University of Michigan, USA (2005)","DOI":"10.3115\/1219840.1219885"},{"key":"393_CR12","unstructured":"Fushimi, S., Kitsuregawa, M., Tanaka, H.: An overview of the system software of a parallel relational database machine grace. In: VLDB (1986)"},{"key":"393_CR13","doi-asserted-by":"crossref","unstructured":"Ghazal, A., Rabl, T., Hu, M., Raab, F., Poess, M., Crolotte, A., Jacobsen, H.-A.: Bigbench: towards an industry standard benchmark for big data analytics. In: SIGMOD Conference (2013)","DOI":"10.1145\/2463676.2463712"},{"key":"393_CR14","unstructured":"Hewitt, C., Bishop, P., Steiger, R.: A universal modular actor formalism for artificial intelligence. In: IJCAI (1973)"},{"key":"393_CR15","doi-asserted-by":"crossref","unstructured":"Hu, M., Liu, B.: Mining and summarizing customer reviews. In: SIGKDD, pp. 168\u2013177 (2004)","DOI":"10.1145\/1014052.1014073"},{"key":"393_CR16","doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. SIGOPS Oper. Syst. Rev. 41(3), 59\u201372 ( 2007)","DOI":"10.1145\/1272998.1273005"},{"key":"393_CR17","doi-asserted-by":"crossref","unstructured":"Isard, M., Yu, Y.: Distributed data-parallel computing using a high-level programming language. In: SIGMOD Conference (2009)","DOI":"10.1145\/1559845.1559962"},{"key":"393_CR18","doi-asserted-by":"crossref","unstructured":"Jestes, J., Li, F., Yan, Z., Yi, K.: Probabilistic string similarity joins. In: SIGMOD, pp. 327\u2013338 (2010)","DOI":"10.1145\/1807167.1807204"},{"key":"393_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, D., Ooi, B.C., Shi, L., Wu, S.: The performance of mapreduce: an in-depth study. PVLDB 3(1\u20132), 472\u2013483 (2010)","DOI":"10.14778\/1920841.1920903"},{"key":"393_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, D., Tung, A.K.H., Chen, G.: Map-join-reduce: toward scalable and efficient data analysis on large clusters. IEEE Trans. Knowl. Data Eng. 23(9) (2011)","DOI":"10.1109\/TKDE.2010.248"},{"key":"393_CR21","doi-asserted-by":"crossref","unstructured":"Li, F., Ooi, B.C., \u00d6zsu, M.T., Wu, S.: Distributed data management using mapreduce. ACM Comput. Surv. 46(3) (2014). doi: 10.1145\/2503009","DOI":"10.1145\/2503009"},{"issue":"3","key":"393_CR22","doi-asserted-by":"crossref","first-page":"253","DOI":"10.14778\/2078331.2078340","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. Proc. VLDB Endow. 5(3), 253\u2013264 (2011)","journal-title":"Proc. VLDB Endow."},{"key":"393_CR23","volume-title":"Symmetric Functions and Hall Polynomials","author":"I Macdonald","year":"1998","unstructured":"Macdonald, I.: Symmetric Functions and Hall Polynomials, 2nd edn. Clarendon Press, Oxford (1998)","edition":"2"},{"key":"393_CR24","doi-asserted-by":"crossref","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J.C., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: a system for large-scale graph processing. In: SIGMOD Conference (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"393_CR25","doi-asserted-by":"crossref","unstructured":"Neumeyer, L., Robbins, B., Nair, A., Kesari. A.: S4: Distributed stream computing platform. In: ICDMW, pp. 170\u2013177 (2010)","DOI":"10.1109\/ICDMW.2010.172"},{"key":"393_CR26","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. Technical Report 1999-66, Stanford InfoLab (1999). Previous number = SIDL-WP-1999-0120"},{"key":"393_CR27","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D.J., DeWitt, D.J., Madden, S., Stonebraker, M.: A comparison of approaches to large-scale data analysis. In: SIGMOD Conference (2009)","DOI":"10.1145\/1559845.1559865"},{"key":"393_CR28","doi-asserted-by":"crossref","unstructured":"Salihoglu, S., Widom, J.: Gps: a graph processing system. In: SSDBM Technical Report (2013)","DOI":"10.1145\/2484838.2484843"},{"key":"393_CR29","unstructured":"Sinha, R., Zobel, J.: Cache-conscious sorting of large sets of strings with dynamic tries. J. Exp. Algorithmics 9, 93\u2013105 (2004)"},{"key":"393_CR30","unstructured":"Stonebraker, M., Abadi, D.J., Batkin, A., Chen, X., Cherniack, M., Ferreira, M., Lau, E., Lin, A., Madden, S., O\u2019Neil, E., O\u2019Neil, P., Rasin, A., Tran, N., Zdonik, S.: C-store: a column-oriented DBMS. In: VLDB (2005)"},{"key":"393_CR31","doi-asserted-by":"crossref","unstructured":"Su, X., Swart, G.: Oracle in-database hadoop: when mapreduce meets rdbms. In: SIGMOD Conference, pp. 779\u2013790 (2012)","DOI":"10.1145\/2213836.2213955"},{"key":"393_CR32","unstructured":"The hadoop offical website. http:\/\/hadoop.apache.org\/"},{"key":"393_CR33","unstructured":"The storm project offical website. http:\/\/storm-project.net\/"},{"key":"393_CR34","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Sarma, J.S., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive: a warehousing solution over a map-reduce framework. VLDB 2(2), 1626\u20131629 (2009)","DOI":"10.14778\/1687553.1687609"},{"key":"393_CR35","doi-asserted-by":"crossref","unstructured":"Wu, S., Li, F., Mehrotra, S., Ooi, B.C.: Query optimization for massively parallel data processing. In: SoCC (2011)","DOI":"10.1145\/2038916.2038928"},{"key":"393_CR36","doi-asserted-by":"crossref","unstructured":"Yang, H., Dasdan, A., Hsiao, R., Parker, D.S.: Map-reduce-merge: simplified relational data processing on large clusters. In: SIGMOD Conference (2007)","DOI":"10.1145\/1247480.1247602"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0393-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-015-0393-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-015-0393-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,5]],"date-time":"2020-09-05T13:03:35Z","timestamp":1599311015000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-015-0393-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,23]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["393"],"URL":"https:\/\/doi.org\/10.1007\/s00778-015-0393-2","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2015,7,23]]}}}