{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:34:20Z","timestamp":1761597260309},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,3,2]],"date-time":"2011-03-02T00:00:00Z","timestamp":1299024000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1007\/s00778-011-0223-0","type":"journal-article","created":{"date-parts":[[2011,3,1]],"date-time":"2011-03-01T21:41:52Z","timestamp":1299015712000},"page":"209-226","source":"Crossref","is-referenced-by-count":28,"title":["Harvesting relational tables from lists on the web"],"prefix":"10.1007","volume":"20","author":[{"given":"Hazem","family":"Elmeleegy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jayant","family":"Madhavan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alon","family":"Halevy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,3,2]]},"reference":[{"key":"223_CR1","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from Web pages. In: SIGMOD (2003)","DOI":"10.1145\/872757.872799"},{"key":"223_CR2","unstructured":"Barish, G., Shin Chen, Y., Dipasquo, D., Knoblock, C.A., Minton, S., Muslea, I., Shahabi, C.: Theaterloc: using information integration technology to rapidly build virtual applications. In: ICDE (2000)"},{"issue":"2","key":"223_CR3","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/0022-2836(87)90316-0","volume":"198","author":"G. Barton","year":"1987","unstructured":"Barton G., Sternberg M.: A strategy for the rapid multiple alignment of protein sequences: confidence levels from tertiary structure comparisons. J. Mol. Biol. 198(2), 327\u2013337 (1987)","journal-title":"J. Mol. Biol."},{"issue":"6","key":"223_CR4","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1145\/366573.366611","volume":"4","author":"R. Bellman","year":"1961","unstructured":"Bellman R.: On the approximation of curves by line segments using dynamic programming. Commun. ACM 4(6), 284 (1961)","journal-title":"Commun. ACM"},{"key":"223_CR5","doi-asserted-by":"crossref","unstructured":"Borkar, V., Deshmukh, K., Sarawagi, S.: Automatic segmentation of text into structured records. In: SIGMOD (2001)","DOI":"10.1145\/375663.375682"},{"key":"223_CR6","unstructured":"Brants, T., Popat, A.C., Xu, P., Och, F.J., Dean, J.: Large language models in machine translation. In: EMNLP-CoNLL (2007)"},{"issue":"1","key":"223_CR7","first-page":"1090","volume":"2","author":"M. Cafarella","year":"2009","unstructured":"Cafarella M., Halevy A., Khoussainova N.: Data integration for the relational Web. PVLDB 2(1), 1090\u20131101 (2009)","journal-title":"PVLDB"},{"issue":"1","key":"223_CR8","first-page":"538","volume":"1","author":"M.J. Cafarella","year":"2008","unstructured":"Cafarella M.J., Halevy A.Y., Wang D.Z., Wu E., Zhang Y.: WebTables: exploring the power of tables on the web. PVLDB 1(1), 538\u2013549 (2008)","journal-title":"PVLDB"},{"key":"223_CR9","unstructured":"Cafarella, M.J., Halevy, A.Y., Zhang, Y., Wang, D.Z., Wu, E.: Uncovering the relational Web. In: WebDB (2008)"},{"key":"223_CR10","doi-asserted-by":"crossref","unstructured":"Chang, C.-H., Lui S.-C.: IEPAD: information extraction based on pattern discovery. In: WWW (2001)","DOI":"10.1145\/371920.372182"},{"key":"223_CR11","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Hurst, M., Jensen, L.S.: A flexible learning system for wrapping tables and lists in HTML documents. In: WWW (2002)","DOI":"10.1145\/511475.511477"},{"key":"223_CR12","doi-asserted-by":"crossref","unstructured":"Cortez, E., da Silva, A.S., Goncalves, M.A., de Moura, E.S.: Ondux: on-demand unsupervised learning for information extraction. In: SIGMOD (2010)","DOI":"10.1145\/1807167.1807254"},{"key":"223_CR13","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: RoadRunner: towards automatic data extraction from large Web sites. In: VLDB (2001)","DOI":"10.1145\/564772.564778"},{"key":"223_CR14","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.sbi.2006.04.004","volume":"3","author":"R.C. Edgar","year":"2006","unstructured":"Edgar R.C., Batzoglou S.: Multiple sequence alignment. Curr. Opin. Struct. Biol. 3, 368\u2013373 (2006)","journal-title":"Curr. Opin. Struct. Biol."},{"issue":"1","key":"223_CR15","first-page":"1078","volume":"2","author":"H. Elmeleegy","year":"2009","unstructured":"Elmeleegy H., Madhavan J., Halevy A.: Harvesting relational tables from lists on the web. PVLDB 2(1), 1078\u20131089 (2009)","journal-title":"PVLDB"},{"key":"223_CR16","doi-asserted-by":"crossref","unstructured":"Embley, D.W., Jiang, Y., Ng, Y.-K.: Record-boundary discovery in Web documents. In: SIGMOD (1999)","DOI":"10.1145\/304182.304223"},{"key":"223_CR17","doi-asserted-by":"crossref","unstructured":"Gonzalez, H., Halevy, A.Y., Jensen, C.S., Langen, A., Madhavan, J., Shapley, R., Shen, W., Goldberg-Kidon, J.: Google fusion tables: web-centered data management and collaboration. In: SIGMOD (2010)","DOI":"10.1145\/1807167.1807286"},{"issue":"1","key":"223_CR18","first-page":"289","volume":"2","author":"R. Gupta","year":"2009","unstructured":"Gupta R., Sarawagi S.: Answering table augmentation queries from unstructured lists on the web. PVLDB 2(1), 289\u2013300 (2009)","journal-title":"PVLDB"},{"key":"223_CR19","unstructured":"Kushmerick, N., Weld, D.S., Doorenbos, R.: Wrapper induction for information extraction. In: IJCAI (1997)"},{"key":"223_CR20","doi-asserted-by":"crossref","unstructured":"Lerman, K., Getoor, L., Minton, S., Knoblock, C.: Using the structure of Web sites for automatic segmentation of tables. In: SIGMOD (2004)","DOI":"10.1145\/1007568.1007584"},{"key":"223_CR21","unstructured":"List of Indonesian floral emblems. http:\/\/en.wikipedia.org\/wiki\/List_of_Indonesian_floral_emblems"},{"key":"223_CR22","unstructured":"Liu, L., Pu, C., Han, W.: XWRAP: an XML-enabled wrapper construction system for Web information sources. In: ICDE (2000)"},{"issue":"2","key":"223_CR23","first-page":"1241","volume":"1","author":"J. Madhavan","year":"2008","unstructured":"Madhavan J., Ko D., Kot L., Ganapathy V., Rasmussen A., Halevy A.Y.: Google\u2019s deep web crawl. PVLDB 1(2), 1241\u20131252 (2008)","journal-title":"PVLDB"},{"key":"223_CR24","doi-asserted-by":"crossref","unstructured":"Miao, G., Tatemura, J., Hsiung, W.-O., Sawires, A., Moser, L.E.: Extracting data records from the web using tag path clustering. In: WWW (2009)","DOI":"10.1145\/1526709.1526841"},{"issue":"3","key":"223_CR25","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s10032-007-0052-2","volume":"10","author":"M. Michelson","year":"2007","unstructured":"Michelson M., Knoblock C.: Unsupervised information extraction from unstructured, ungrammatical data sources on the World Wide Web. IJDAR 10(3), 211\u2013226 (2007)","journal-title":"IJDAR"},{"issue":"3","key":"223_CR26","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"S.B. Needleman","year":"1970","unstructured":"Needleman S.B., Wunsch C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48(3), 443\u2013453 (1970)","journal-title":"J. Mol. Biol."},{"issue":"1","key":"223_CR27","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1517\/14622416.3.1.131","volume":"3","author":"C. Notredame","year":"2002","unstructured":"Notredame C.: Recent progresses in multiple sequence alignment: a survey. Pharmacogenomics 3(1), 327\u2013337 (2002)","journal-title":"Pharmacogenomics"},{"key":"223_CR28","doi-asserted-by":"crossref","unstructured":"Talukdar, P.P., Reisinger, J., Pasca, M., Ravichandran, D., Bhagat, R., Pereira, F.: Weakly supervised acquisition of labeled class instances using graph random walks. In: EMNLP (2008)","DOI":"10.3115\/1613715.1613787"},{"key":"223_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Lochovsky, F.H.: Data extraction and label assignment for web databases. In: WWW (2003)","DOI":"10.1145\/775152.775179"},{"key":"223_CR30","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Liu, B.: Web data extraction based on partial tree alignment. In: WWW (2005)","DOI":"10.1145\/1060745.1060761"},{"issue":"2","key":"223_CR31","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s11280-007-0022-0","volume":"10","author":"Y. Zhai","year":"2007","unstructured":"Zhai Y., Liu B.: Extracting Web data using instance-based learning. WWW 10(2), 113\u2013132 (2007)","journal-title":"WWW"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-011-0223-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-011-0223-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-011-0223-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T19:05:35Z","timestamp":1560020735000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-011-0223-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,3,2]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,4]]}},"alternative-id":["223"],"URL":"https:\/\/doi.org\/10.1007\/s00778-011-0223-0","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,3,2]]}}}