{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:16:44Z","timestamp":1763468204888,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,8,24]],"date-time":"2014-08-24T00:00:00Z","timestamp":1408838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000145","name":"Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-1064606","IIS-1054913"],"award-info":[{"award-number":["IIS-1064606","IIS-1054913"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yahoo!"},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004341","name":"Dow Chemical Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,8,24]]},"DOI":"10.1145\/2623330.2623617","type":"proceedings-article","created":{"date-parts":[[2014,8,22]],"date-time":"2014-08-22T19:38:46Z","timestamp":1408736326000},"page":"1126-1135","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":50,"title":["Integrating spreadsheet data via accurate and low-effort extraction"],"prefix":"10.1145","author":[{"given":"Zhe","family":"Chen","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"given":"Michael","family":"Cafarella","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]}],"member":"320","published-online":{"date-parts":[[2014,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvlc.2006.06.001"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2003.1240305"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453916"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687750"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559857"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509908.2509909"},{"key":"e_1_3_2_2_8_1","volume-title":"A semiautomatic approach for accurate and low-effort spreadsheet data extraction. Technical report","author":"Chen Z.","year":"2014","unstructured":"Z. Chen and M. Cafarella . A semiautomatic approach for accurate and low-effort spreadsheet data extraction. Technical report , University of Michigan , 2014 . Z. Chen and M. Cafarella. A semiautomatic approach for accurate and low-effort spreadsheet data extraction. Technical report, University of Michigan, 2014."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536274.2536276"},{"key":"e_1_3_2_2_10_1","unstructured":"2009. ClueWeb09 http:\/\/lemurproject.org\/clueweb09.php\/.  2009. ClueWeb09 http:\/\/lemurproject.org\/clueweb09.php\/."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90060-D"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1480945.1480972"},{"key":"e_1_3_2_2_13_1","volume-title":"COLT","author":"Dekel O.","year":"2009","unstructured":"O. Dekel and O. Shamir . Vox populi: Collecting high-quality labels from a crowd . In COLT , 2009 . O. Dekel and O. Shamir. Vox populi: Collecting high-quality labels from a crowd. In COLT, 2009."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242583"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047205"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/237661.237688"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063829"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1785162.1785181"},{"key":"e_1_3_2_2_20_1","volume-title":"CIDR","author":"Ives Z. G.","year":"2009","unstructured":"Z. G. Ives , C. A. Knoblock , S. Minton , M. Jacob , P. P. Talukdar , R. Tuchinda , J. L. Ambite , M. Muslea , and C. Gazen . Interactive data integration through smart copy & paste . In CIDR , 2009 . Z. G. Ives, C. A. Knoblock, S. Minton, M. Jacob, P. P. Talukdar, R. Tuchinda, J. L. Ambite, M. Muslea, and C. Gazen. Interactive data integration through smart copy & paste. In CIDR, 2009."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_2_22_1","volume-title":"Probabilistic Graphical Models - Principles and Techniques","author":"Koller D.","year":"2009","unstructured":"D. Koller and N. Friedman . Probabilistic Graphical Models - Principles and Techniques . MIT Press , 2009 . D. Koller and N. Friedman. Probabilistic Graphical Models - Principles and Techniques. MIT Press, 2009."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.200"},{"key":"e_1_3_2_2_24_1","first-page":"282","volume-title":"ICML","author":"Lafferty J.","year":"2001","unstructured":"J. Lafferty , A. McCallum , and F. Pereira . Conditional random fields: Probabilistic models for segmenting and labeling sequence data . In ICML , pages 282 -- 289 , 2001 . J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, pages 282--289, 2001."},{"key":"e_1_3_2_2_25_1","first-page":"134","volume-title":"ICDE","author":"Lakshmanan L. V. S.","year":"1998","unstructured":"L. V. S. Lakshmanan , S. N. Subramanian , N. Goyal , and R. Krishnamurthy . On query spreadsheets . In ICDE , pages 134 -- 141 , 1998 . L. V. S. Lakshmanan, S. N. Subramanian, N. Goyal, and R. Krishnamurthy. On query spreadsheets. In ICDE, pages 134--141, 1998."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336665"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/237091.237097"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1216295.1216328"},{"key":"e_1_3_2_2_29_1","unstructured":"2007. http:\/\/www.di.ens.fr\/ mschmidt\/Software\/UGM.htm  2007. http:\/\/www.di.ens.fr\/ mschmidt\/Software\/UGM.htm"}],"event":{"name":"KDD '14: The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"New York New York USA","acronym":"KDD '14"},"container-title":["Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2623330.2623617","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2623330.2623617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:19:35Z","timestamp":1750231175000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2623330.2623617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,8,24]]},"references-count":29,"alternative-id":["10.1145\/2623330.2623617","10.1145\/2623330"],"URL":"https:\/\/doi.org\/10.1145\/2623330.2623617","relation":{},"subject":[],"published":{"date-parts":[[2014,8,24]]},"assertion":[{"value":"2014-08-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}