{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T05:14:27Z","timestamp":1740028467859,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":45,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642123092"},{"type":"electronic","value":"9783642123108"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-12310-8_6","type":"book-chapter","created":{"date-parts":[[2010,3,15]],"date-time":"2010-03-15T06:50:31Z","timestamp":1268635831000},"page":"94-113","source":"Crossref","is-referenced-by-count":6,"title":["Chapter 6: Web Data Extraction for Service Creation"],"prefix":"10.1007","author":[{"given":"Robert","family":"Baumgartner","sequence":"first","affiliation":[]},{"given":"Alessandro","family":"Campi","sequence":"additional","affiliation":[]},{"given":"Georg","family":"Gottlob","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Herzog","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Adelberg, B.: Nodose - a tool for semi-automatically extracting structured and semistructured data from text documents. In: SIGMOD Record, pp. 283\u2013294 (1998)","DOI":"10.1145\/276304.276330"},{"key":"6_CR2","first-page":"337","volume-title":"SIGMOD 2003: Proceedings of the 2003 ACM SIGMOD international conference on Management of data","author":"A. Arasu","year":"2003","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: SIGMOD 2003: Proceedings of the 2003 ACM SIGMOD international conference on Management of data, pp. 337\u2013348. ACM, New York (2003)"},{"issue":"3","key":"6_CR3","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1002\/(SICI)1096-9942(1999)5:3<127::AID-TAPO2>3.0.CO;2-X","volume":"5","author":"G.O. Arocena","year":"1999","unstructured":"Arocena, G.O., Mendelzon, A.O.: Weboql: restructuring documents, databases, and webs. Theor. Pract. Object Syst.\u00a05(3), 127\u2013141 (1999)","journal-title":"Theor. Pract. Object Syst."},{"key":"6_CR4","unstructured":"Baumgartner, R., Ceresna, M., Lederm\u00fcller, G.: Deep web navigation in web data extraction. In: Proc. of IAWTIC (2005)"},{"key":"6_CR5","series-title":"Lecture Notes in Artificial Intelligence","first-page":"21","volume-title":"Logic Programming and Nonmonotonic Reasoning","author":"R. Baumgartner","year":"2001","unstructured":"Baumgartner, R., Flesca, S., Gottlob, G.: Declarative Information Extraction, Web Crawling and Recursive Wrapping with Lixto. In: Eiter, T., Faber, W., Truszczy\u0144ski, M. (eds.) LPNMR 2001. LNCS (LNAI), vol.\u00a02173, p. 21. Springer, Heidelberg (2001)"},{"key":"6_CR6","unstructured":"Baumgartner, R., Flesca, S., Gottlob, G.: Visual Web Information Extraction with Lixto. In: Proc. of VLDB (2001)"},{"key":"6_CR7","unstructured":"Baumgartner, R., Herzog, M., Gottlob, G.: Visual programming of web data aggregation applications. In: Proc. of IIWeb 2003 (2003)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Baumgartner, R., Gatterbauer, W., Gottlob, G.: Web data extraction system. In: Encyclopedia of Database Systems (2009)","DOI":"10.1007\/978-0-387-39940-9_1154"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Baumgartner, R., Gottlob, G., Herzog, M.: Scalable web data extraction for online market intelligence, vol.\u00a02, pp. 1512\u20131523 (2009)","DOI":"10.14778\/1687553.1687580"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Baumgartner, R., Gottlob, G., Herzog, M., Slany, W.: Interactively Adding Web Service Interfaces to Existing Web Applications. In: Proc. of SAINT (2004)","DOI":"10.1109\/SAINT.2004.1266101"},{"issue":"5","key":"6_CR11","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1504\/IJEB.2004.005884","volume":"2","author":"R. Baumgartner","year":"2004","unstructured":"Baumgartner, R., Herzog, M.: Using Lixto for automating portal-based b2b processes in the automotive industry. International Journal of Electronic Business\u00a02(5), 519\u2013530 (2004)","journal-title":"International Journal of Electronic Business"},{"key":"6_CR12","first-page":"720","volume-title":"EDBT 2008: Proceedings of the 11th international conference on Extending database technology","author":"L. Blanco","year":"2008","unstructured":"Blanco, L., Crescenzi, V., Merialdo, P., Papotti, P.: Flint: Google-basing the web. In: EDBT 2008: Proceedings of the 11th international conference on Extending database technology, pp. 720\u2013724. ACM, New York (2008)"},{"issue":"1","key":"6_CR13","doi-asserted-by":"publisher","first-page":"538","DOI":"10.14778\/1453856.1453916","volume":"1","author":"M.J. Cafarella","year":"2008","unstructured":"Cafarella, M.J., Halevy, A., Wang, D.Z., Wu, E., Zhang, Y.: Webtables: exploring the power of tables on the web. Proc. VLDB Endow.\u00a01(1), 538\u2013549 (2008)","journal-title":"Proc. VLDB Endow."},{"key":"6_CR14","unstructured":"Cafarella, M.J., R\u00e9, C., Suciu, D., Etzioni, O., Banko, M.: Structured querying of web text: A technical challenge. In: CIDR (2007)"},{"issue":"9","key":"6_CR15","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/S0306-4379(98)00028-3","volume":"23","author":"V. Crescenzi","year":"1998","unstructured":"Crescenzi, V., Mecca, G.: Grammars have exceptions. Inf. Syst.\u00a023(9), 539\u2013565 (1998)","journal-title":"Inf. Syst."},{"issue":"5","key":"6_CR16","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1145\/1017460.1017462","volume":"51","author":"V. Crescenzi","year":"2004","unstructured":"Crescenzi, V., Mecca, G.: Automatic information extraction from large websites. J. ACM\u00a051(5), 731\u2013779 (2004)","journal-title":"J. ACM"},{"key":"6_CR17","first-page":"109","volume-title":"VLDB 2001: Proceedings of the 27th International Conference on Very Large Data Bases","author":"V. Crescenzi","year":"2001","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: Towards automatic data extraction from large web sites. In: VLDB 2001: Proceedings of the 27th International Conference on Very Large Data Bases, pp. 109\u2013118. Morgan Kaufmann Publishers Inc., San Francisco (2001)"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0169-023X(99)00027-0","volume":"31","author":"D.W. Embley","year":"1999","unstructured":"Embley, D.W., Campbell, D.M., Jiang, Y.S., Liddle, S.W., Lonsdale, D.W., Ng, Y.k., Smith, R.D.: Conceptual-model-based data extraction from multiple-record web pages. Data and Knowledge Engineering\u00a031, 227\u2013251 (1999)","journal-title":"Data and Knowledge Engineering"},{"issue":"12","key":"6_CR19","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/1409360.1409378","volume":"51","author":"O. Etzioni","year":"2008","unstructured":"Etzioni, O., Banko, M., Soderland, S., Weld, D.S.: Open information extraction from the web. Commun. ACM\u00a051(12), 68\u201374 (2008)","journal-title":"Commun. ACM"},{"key":"6_CR20","unstructured":"Freitag, D.: Information extraction from html: Application of a general machine learning approach. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 517\u2013523 (1998)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Gatterbauer, W., Bohunsky, P., Herzog, M., Kr\u00fcpl, B., Pollak, B.: Towards domain-independent information extraction from web tables. In: Proc. of WWW, May\u00a08-12 (2007)","DOI":"10.1145\/1242572.1242583"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Gottlob, G., Koch, C.: Monadic Datalog and the Expressive Power of Web Information Extraction Languages. Journal of the ACM 51(1) (2004)","DOI":"10.1145\/962446.962450"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Hammer, J., McHugh, J., Garcia-Molina, H.: Semistructured data: The tsimmis experience. In: Proceedings of the First East-European Workshop on Advances in Databases and Information Systems, ADBIS 1997, pp. 1\u20138 (1997)","DOI":"10.14236\/ewic\/ADBIS1997.22"},{"key":"6_CR24","first-page":"217","volume-title":"SIGMOD 2003: Proceedings of the 2003 ACM SIGMOD international conference on Management of data","author":"B. He","year":"2003","unstructured":"He, B., Chang, K.C.-C.: Statistical schema matching across web query interfaces. In: SIGMOD 2003: Proceedings of the 2003 ACM SIGMOD international conference on Management of data, pp. 217\u2013228. ACM, New York (2003)"},{"key":"6_CR25","unstructured":"He, B., Zhang, Z., Chang, K.C.-C.: Towards building a metaquerier: Extracting and matching web query interfaces. In: International Conference on Data Engineering, pp. 1098\u20131099 (2005)"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Herzog, M., Gottlob, G.: InfoPipes: A flexible framework for M-Commerce applications. In: Proc. of TES workshop at VLDB (2001)","DOI":"10.1007\/3-540-44809-8_13"},{"key":"6_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-642-04409-0_46","volume-title":"Web Information Systems Engineering - WISE 2009","author":"W. Holzinger","year":"2009","unstructured":"Holzinger, W., Kr\u00fcpl, B., Baumgartner, R.: Automated ontology-driven metasearch generation with metamorph. In: Vossen, G., Long, D.D.E., Yu, J.X. (eds.) WISE 2009. LNCS, vol.\u00a05802, pp. 473\u2013480. Springer, Heidelberg (2009)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Chang, C.h., Lui, S.-C.: Iepad: Information extraction based on pattern discovery, pp. 681\u2013688 (2001)","DOI":"10.1145\/371920.372182"},{"key":"6_CR29","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-540-85563-7_59","volume-title":"Knowledge-Based Intelligent Information and Engineering Systems","author":"D. Juri\u0107","year":"2008","unstructured":"Juri\u0107, D., Banek, M., Sko\u010dir, Z.: Uncovering the deep web: Transferring relational database content and metadata to OWL ontologies. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008, Part I. LNCS (LNAI), vol.\u00a05177, pp. 456\u2013463. Springer, Heidelberg (2008)"},{"issue":"10","key":"6_CR30","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"M. Kayed","year":"2006","unstructured":"Kayed, M., Shaalan, K.F.: A survey of web information extraction systems. IEEE Trans. on Knowl. and Data Eng.\u00a018(10), 1411\u20131428 (2006); Member-Chang, Chia-Hui and Member-Girgis, Moheb Ramzy","journal-title":"IEEE Trans. on Knowl. and Data Eng."},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Knoblock, C.A., Lerman, K., Minton, S., Muslea, I.: Accurately and reliably extracting data from the web: a machine learning approach, pp. 275\u2013287 (2003)","DOI":"10.1007\/978-3-7908-1772-0_17"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"2000","DOI":"10.1016\/S0004-3702(99)00100-9","volume":"118","author":"N. Kushmerick","year":"2000","unstructured":"Kushmerick, N.: Wrapper induction: Efficiency and expressiveness. Artificial Intelligence\u00a0118, 2000 (2000)","journal-title":"Artificial Intelligence"},{"issue":"2","key":"6_CR33","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/S0169-023X(01)00047-7","volume":"40","author":"A.H.F. Laender","year":"2002","unstructured":"Laender, A.H.F., Ribeiro-Neto, B., da Silva, A.S.: Debye - date extraction by example. Data Knowl. Eng.\u00a040(2), 121\u2013154 (2002)","journal-title":"Data Knowl. Eng."},{"issue":"2","key":"6_CR34","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/565117.565137","volume":"31","author":"A.H.F. Laender","year":"2002","unstructured":"Laender, A.H.F., Ribeiro-Neto, B.A., da Silva, A.S., Teixeira, J.S.: A brief survey of web data extraction tools. SIGMOD Rec.\u00a031(2), 84\u201393 (2002)","journal-title":"SIGMOD Rec."},{"key":"6_CR35","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1145\/1007568.1007584","volume-title":"SIGMOD 2004: Proceedings of the 2004 ACM SIGMOD international conference on Management of data","author":"K. Lerman","year":"2004","unstructured":"Lerman, K., Getoor, L., Minton, S., Knoblock, C.: Using the structure of web sites for automatic segmentation of tables. In: SIGMOD 2004: Proceedings of the 2004 ACM SIGMOD international conference on Management of data, pp. 119\u2013130. ACM, New York (2004)"},{"issue":"1","key":"6_CR36","first-page":"149","volume":"18","author":"K. Lerman","year":"2003","unstructured":"Lerman, K., Minton, S.N., Knoblock, C.A.: Wrapper maintenance: a machine learning approach. J. Artif. Int. Res.\u00a018(1), 149\u2013181 (2003)","journal-title":"J. Artif. Int. Res."},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Liu, L., Pu, C., Han, W.: Xwrap: An xml-enabled wrapper construction system for web information sources. In: ICDE, pp. 611\u2013621 (2000)","DOI":"10.1109\/ICDE.2000.839475"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Raposo, J., Pan, A., Alvarez, M., Hidalgo, J., Vina, A.: The Wargo System: Semi-Automatic Wrapper Generation in Presence of Complex Data Access Modes. In: Proceedings of DEXA 2002, Aix-en-Provence, France (2002)","DOI":"10.1109\/DEXA.2002.1045916"},{"key":"6_CR39","first-page":"811","volume-title":"Proceedings of the Eleventh National Conference on Artificial Intelligence","author":"E. Riloff","year":"1993","unstructured":"Riloff, E.: Automatically constructing a dictionary for information extraction tasks. In: Proceedings of the Eleventh National Conference on Artificial Intelligence, pp. 811\u2013816. MIT Press, Cambridge (1993)"},{"issue":"3","key":"6_CR40","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/S0169-023X(00)00051-3","volume":"36","author":"A. Sahuguet","year":"2001","unstructured":"Sahuguet, A., Azavant, F.: Building intelligent web applications using lightweight wrappers. Data Knowl. Eng.\u00a036(3), 283\u2013316 (2001)","journal-title":"Data Knowl. Eng."},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Shen, W., Derose, P., Vu, L., Doan, A., Ramakrishnan, R.: Source-aware entity matching: A compositional approach. In: IEEE 23rd International Conference on Data Engineering, ICDE 2007, pp. 196\u2013205 (2007)","DOI":"10.1109\/ICDE.2007.367865"},{"key":"6_CR42","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1145\/1376616.1376718","volume-title":"SIGMOD 2008: Proceedings of the 2008 ACM SIGMOD international conference on Management of data","author":"W. Shen","year":"2008","unstructured":"Shen, W., DeRose, P., McCann, R., Doan, A., Ramakrishnan, R.: Toward best-effort information extraction. In: SIGMOD 2008: Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pp. 1031\u20131042. ACM, New York (2008)"},{"key":"6_CR43","unstructured":"Shen, W., Doan, A., Naughton, J.F., Ramakrishnan, R.: Declarative information extraction using datalog with embedded extraction predicates. In: VLDB 2007: Proceedings of the 33rd international conference on Very large data bases, pp. 1033\u20131044. VLDB Endowment (2007)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Soderland, S., Cardie, C., Mooney, R.: Learning information extraction rules for semi-structured and free text. Machine Learning, 233\u2013272 (1999)","DOI":"10.1023\/A:1007562322031"},{"key":"6_CR45","first-page":"1314","volume-title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence","author":"S. Soderland","year":"1995","unstructured":"Soderland, S., Fisher, D., Aseltine, J., Lehnert, W.: Crystal: Inducing a conceptual dictionary. In: Mellish, C. (ed.) Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pp. 1314\u20131319. Morgan Kaufmann, San Francisco (1995)"}],"container-title":["Lecture Notes in Computer Science","Search Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-12310-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T12:57:27Z","timestamp":1739969847000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-12310-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642123092","9783642123108"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-12310-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}