{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T20:21:43Z","timestamp":1730319703902,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T00:00:00Z","timestamp":1558915200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1513407, IIS-1633755, IIS-1733878 and IIS-1652750"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,5,27]]},"DOI":"10.1145\/3183713.3183746","type":"proceedings-article","created":{"date-parts":[[2018,5,25]],"date-time":"2018-05-25T12:39:28Z","timestamp":1527251968000},"page":"943-958","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Navigating the Data Lake with DATAMARAN"],"prefix":"10.1145","author":[{"given":"Yihan","family":"Gao","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Silu","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Aditya","family":"Parameswaran","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2018,5,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Datamaran technical report. https:\/\/arxiv.org\/abs\/1708.08905. Datamaran technical report. https:\/\/arxiv.org\/abs\/1708.08905."},{"key":"e_1_3_2_1_2_1","unstructured":"Flex: lexical analyzer generator. https:\/\/en.wikipedia.org\/wiki\/Flex_(lexical_analyser_generator). Flex: lexical analyzer generator. https:\/\/en.wikipedia.org\/wiki\/Flex_(lexical_analyser_generator)."},{"key":"e_1_3_2_1_3_1","unstructured":"Recordbreaker: Automatic structure for your text-formatted data. http:\/\/cloudera.github.io\/RecordBreaker\/. Recordbreaker: Automatic structure for your text-formatted data. http:\/\/cloudera.github.io\/RecordBreaker\/."},{"key":"e_1_3_2_1_4_1","unstructured":"Stack exchange data dump. https:\/\/archive.org\/details\/stackexchange. Accessed: 2017-07-13. Stack exchange data dump. https:\/\/archive.org\/details\/stackexchange. Accessed: 2017-07-13."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014058"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/336597.336644"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.2011.28"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872799"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2813885.2737952"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.720554"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2590296.2590346"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453916"},{"key":"e_1_3_2_1_13_1","volume-title":"Data services leveraging bing's data assets. Data Engineering, page 15","author":"Chakrabarti K.","year":"2016","unstructured":"K. Chakrabarti Data services leveraging bing's data assets. Data Engineering, page 15 , 2016 . K. Chakrabarti et al. Data services leveraging bing's data assets. Data Engineering, page 15, 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"EMNLP","author":"Cohen S. B.","year":"2011","unstructured":"S. B. Cohen , D. Das , and N. A. Smith . Unsupervised structure prediction with non-parallel multilingual guidance . In EMNLP , 2011 . S. B. Cohen, D. Das, and N. A. Smith. Unsupervised structure prediction with non-parallel multilingual guidance. In EMNLP, 2011."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511477"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989380"},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"USENIX Security Symposium","author":"Cui W.","year":"2007","unstructured":"W. Cui , J. Kannan , and H. J. Wang . Discoverer: Automatic protocol reverse engineering from network traces . In USENIX Security Symposium , pages 1 -- 14 , 2007 . W. Cui, J. Kannan, and H. J. Wang. Discoverer: Automatic protocol reverse engineering from network traces. In USENIX Security Symposium, pages 1--14, 2007."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687749"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988687"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1328897.1328488"},{"key":"e_1_3_2_1_21_1","first-page":"577","volume-title":"AAAI\/IAAI","author":"Freitag D.","year":"2000","unstructured":"D. Freitag and N. Kushmerick . Boosted wrapper induction . In AAAI\/IAAI , pages 577 -- 583 , 2000 . D. Freitag and N. Kushmerick. Boosted wrapper induction. In AAAI\/IAAI, pages 577--583, 2000."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807158"},{"key":"e_1_3_2_1_23_1","volume-title":"Parsing techniques: a practical guide","author":"Grune D.","year":"2007","unstructured":"D. Grune and C. J. Jacobs . Parsing techniques: a practical guide . Springer Science &Business Media , 2007 . D. Grune and C. J. Jacobs. Parsing techniques: a practical guide. Springer Science &Business Media, 2007."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1926385.1926423"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1925844.1926423"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2240236.2240260"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047205"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687661"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2899389"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903730"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/603867.603873"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/306766.306775"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064034"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/925772"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2666356.2594333"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/1613715.1613719"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1921005"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935894"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557154"},{"key":"e_1_3_2_1_41_1","volume-title":"AAAI: Workshop on AI and Information Integration","author":"Muslea I.","year":"1998","unstructured":"I. Muslea , S. Minton , and C. Knoblock . Stalker: Learning extraction rules for semistructured, web-based information sources . In AAAI: Workshop on AI and Information Integration , 1998 . I. Muslea, S. Minton, and C. Knoblock. Stalker: Learning extraction rules for semistructured, web-based information sources. In AAAI: Workshop on AI and Information Integration, 1998."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559882"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767842"},{"key":"e_1_3_2_1_44_1","first-page":"381","volume-title":"VLDB","volume":"1","author":"Raman V.","year":"2001","unstructured":"V. Raman and J. M. Hellerstein . Potter's wheel: An interactive data cleaning system . In VLDB , volume 1 , pages 381 -- 390 , 2001 . V. Raman and J. M. Hellerstein. Potter's wheel: An interactive data cleaning system. In VLDB, volume 1, pages 381--390, 2001."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10668"},{"key":"e_1_3_2_1_46_1","volume-title":"Gartner http:\/\/www.gartner.com\/newsroom\/id\/2809117","author":"Rivera J.","year":"2014","unstructured":"J. Rivera and R. van der Meulen . Gartner says beware of the data lake fallacy . In Gartner http:\/\/www.gartner.com\/newsroom\/id\/2809117 , 2014 . J. Rivera and R. van der Meulen. Gartner says beware of the data lake fallacy. In Gartner http:\/\/www.gartner.com\/newsroom\/id\/2809117, 2014."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000003"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213962"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458502.1458505"},{"key":"e_1_3_2_1_50_1","volume-title":"Introduction to the Theory of Computation","author":"Sipser M.","year":"2006","unstructured":"M. Sipser . Introduction to the Theory of Computation , volume 2 . Thomson Course Technology Boston , 2006 . M. Sipser. Introduction to the Theory of Computation, volume 2. Thomson Course Technology Boston, 2006."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2012.10.009"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.161"},{"key":"e_1_3_2_1_53_1","volume-title":"EMNLP","author":"Spitkovsky V. I.","year":"2011","unstructured":"V. I. Spitkovsky , H. Alshawi , A. X. Chang , and D. Jurafsky . Unsupervised dependency parsing without gold part-of-speech tags . In EMNLP , 2011 . V. I. Spitkovsky, H. Alshawi, A. X. Chang, and D. Jurafsky. Unsupervised dependency parsing without gold part-of-speech tags. In EMNLP, 2011."},{"key":"e_1_3_2_1_54_1","volume-title":"The enterprise data lake: Better integration and deeper analytics. PwC Technology Forecast: Rethinking integration, (1)","author":"Stein B.","year":"2014","unstructured":"B. Stein and A. Morrison . The enterprise data lake: Better integration and deeper analytics. PwC Technology Forecast: Rethinking integration, (1) , 2014 . B. Stein and A. Morrison. The enterprise data lake: Better integration and deeper analytics. PwC Technology Forecast: Rethinking integration, (1), 2014."},{"key":"e_1_3_2_1_55_1","volume-title":"CIDR","author":"Terrizzano I.","year":"2015","unstructured":"I. Terrizzano , P. M. Schwarz , M. Roth , and J. E. Colino . Data wrangling: The challenging yourney from the wild to the lake . In CIDR , 2015 . I. Terrizzano, P. M. Schwarz, M. Roth, and J. E. Colino. Data wrangling: The challenging yourney from the wild to the lake. In CIDR, 2015."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30179-0_27"},{"key":"e_1_3_2_1_57_1","first-page":"109","volume-title":"VLDB","year":"2001","unstructured":"Valter Crescenzi et. al. Roadrunner : Towards automatic data extraction from large web sites . In VLDB , pages 109 -- 118 , 2001 . Valter Crescenzi et. al. Roadrunner: Towards automatic data extraction from large web sites. In VLDB, pages 109--118, 2001."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.14778\/2002938.2002939"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2012.6459963"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.5555\/2025968.2025970"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16161-2_24"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213848"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060761"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465276"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972788.38"}],"event":{"name":"SIGMOD\/PODS '18: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Houston TX USA","acronym":"SIGMOD\/PODS '18"},"container-title":["Proceedings of the 2018 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3183713.3183746","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3183713.3183746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T08:25:18Z","timestamp":1673425518000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3183713.3183746"}},"subtitle":["Automatically Extracting Structure from Log Datasets"],"short-title":[],"issued":{"date-parts":[[2018,5,27]]},"references-count":65,"alternative-id":["10.1145\/3183713.3183746","10.1145\/3183713"],"URL":"https:\/\/doi.org\/10.1145\/3183713.3183746","relation":{},"subject":[],"published":{"date-parts":[[2018,5,27]]},"assertion":[{"value":"2018-05-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}