{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:34:32Z","timestamp":1725471272537},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540359692"},{"type":"electronic","value":"9783540359715"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11788911_1","type":"book-chapter","created":{"date-parts":[[2006,9,25]],"date-time":"2006-09-25T09:15:34Z","timestamp":1159175734000},"page":"1-15","source":"Crossref","is-referenced-by-count":7,"title":["The Lixto Project: Exploring New Frontiers of Web Data Extraction"],"prefix":"10.1007","author":[{"given":"Julien","family":"Carme","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michal","family":"Ceresna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Fr\u00f6lich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Gottlob","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamir","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Herzog","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Holzinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernhard","family":"Kr\u00fcpl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"1_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10032-002-0080-x","volume":"5","author":"M. Aiello","year":"2002","unstructured":"Aiello, M., Monz, C., Todoran, L., Worring, M.: Document understanding for a broad class of documents. Int. J. of Document Anal. and Recog.\u00a05(1), 1\u201316 (2002)","journal-title":"Int. J. of Document Anal. and Recog."},{"issue":"1","key":"1_CR2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/PL00013569","volume":"4","author":"O. Altamura","year":"2001","unstructured":"Altamura, O., Esposito, F., Malerba, D.: Transforming Paper Documents into XML Format with WISDOM++. Intl. J. of Doc. Anal. and Recog.\u00a04(1), 2\u201317 (2001)","journal-title":"Intl. J. of Doc. Anal. and Recog."},{"key":"1_CR3","unstructured":"Baumgartner, R., Flesca, S., Gottlob, G.: Visual Web Information Extraction with Lixto. In: Proceedings of the 27th International Conference on Very Large Data Bases (VLDB 2001), Rome, Italy, pp. 119\u2013128 (2001)"},{"key":"1_CR4","unstructured":"Baumgartner, R., Ceresna, M., Lederm\u00fcller, G.: Automating Web Navigation in Web Data Extraction. In: Proceedings of International Conference on Intelligent Agents, Vienna, Austria (to appear, 2005)"},{"issue":"4","key":"1_CR5","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1145\/76359.76371","volume":"36","author":"A. Blumer","year":"1989","unstructured":"Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Learnability and the Vapnik-Chervonenkis dimension. J. ACM\u00a036(4), 929\u2013965 (1989)","journal-title":"J. ACM"},{"issue":"11\u201316","key":"1_CR6","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1016\/S1389-1286(99)00052-3","volume":"31","author":"S. Chakrabarti","year":"1999","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B.: Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery. Computer Networks\u00a031(11\u201316), 1623\u20131640 (1999)","journal-title":"Computer Networks"},{"key":"1_CR7","unstructured":"Ceresna, M., Gottlob, G.: Query Based Learning of XPath Fragments. In: Proceedings of Dagstuhl Seminar on Machine Learning for the Semantic Web (05071), Dagstuhl, Germany (2005)"},{"key":"1_CR8","unstructured":"Embley, D.W.: Toward Semantic Understanding \u2013 An Approach Based on Information Extraction Ontologies. In: Proceedings of the Fifteenth Australasian Database Conference, Dunedin, New Zealand, p. 3 (2004)"},{"key":"1_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/11611257_3","volume-title":"SOFSEM 2006: Theory and Practice of Computer Science","author":"G. Gottlob","year":"2006","unstructured":"Gottlob, G., Koch, C.: A Formal Comparison of Visual Web Wrapper Generators. In: Wiedermann, J., Tel, G., Pokorn\u00fd, J., Bielikov\u00e1, M., \u0160tuller, J. (eds.) SOFSEM 2006. LNCS, vol.\u00a03831, pp. 30\u201348. Springer, Heidelberg (2006)"},{"issue":"1","key":"1_CR10","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1145\/962446.962450","volume":"51","author":"G. Gottlob","year":"2004","unstructured":"Gottlob, G., Koch, C.: Monadic datalog and the expressive power of languages for Web information extraction. J. ACM\u00a051(1), 74\u2013113 (2004)","journal-title":"J. ACM"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Gottlob, G., Koch, C., Baumgartner, R., Herzog, M., Flesca, S.: The Lixto Data Extraction Project - Back and Forth between Theory and Practice. In: Proceedings of the Twenty-third ACM SIGACT-SIGMOD-SIGAR Symposium on Principles of Database Systems, Paris, France, pp. 1\u201312 (2004)","DOI":"10.1145\/1055558.1055560"},{"issue":"2","key":"1_CR12","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1145\/1071610.1071614","volume":"30","author":"G. Gottlob","year":"2005","unstructured":"Gottlob, G., Koch, C., Pichler, R.: Efficient algorithms for processing XPath queries. ACM Trans. Database Syst.\u00a030(2), 444\u2013491 (2005)","journal-title":"ACM Trans. Database Syst."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Hassan, T., Baumgartner, R.: Using Graph Matching Techniques to Wrap Data from PDF Documents. In: Proceedings of the 15th International World Wide Web Conference (Poster Track), Edinburgh, UK (to appear, 2006)","DOI":"10.1145\/1135777.1135935"},{"key":"1_CR14","unstructured":"Hurst, M.: The Interpretation of Tables in Texts. PhD thesis, University of Edinburgh (2000)"},{"key":"1_CR15","first-page":"12","volume":"1","author":"V.I. Levenshtein","year":"1965","unstructured":"Levenshtein, V.I.: Binary Codes Capable of Correcting Spurious Insertions and Deletions of Ones. Russian Problemy Peredachi Informatsii\u00a01, 12\u201325 (1965)","journal-title":"Russian Problemy Peredachi Informatsii"},{"issue":"10","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/34.954603","volume":"23","author":"J. Llados","year":"2001","unstructured":"Llados, J., Marti, E., Villanueva, J.J.: Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs. IEEE Tran. on Pattern Anal. and Mach. Intel.\u00a023(10), 1137\u20131143 (2001)","journal-title":"IEEE Tran. on Pattern Anal. and Mach. Intel."},{"issue":"1\u20137","key":"1_CR17","first-page":"107","volume":"30","author":"L. Page","year":"1998","unstructured":"Page, L., Brin, S.: The Anatomy of a Large-Scale Hypertextual Web Search Engine. Computer Networks\u00a030(1\u20137), 107\u2013117 (1998)","journal-title":"Computer Networks"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Silva, A.C., Alipio, J., Torgo, L.: Automatic Selection of Table Areas in Documents for Information Extraction. In: 11th Protuguese Conference on Artificial Intelligence, EPIA, pp. 460\u2013465 (2003)","DOI":"10.1007\/978-3-540-24580-3_54"},{"key":"1_CR19","unstructured":"XML Path Language (XPath), Version 1.0, \n                    \n                      http:\/\/www.w3.org\/TR\/xpath"}],"container-title":["Lecture Notes in Computer Science","Flexible and Efficient Information Handling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11788911_1.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:22:37Z","timestamp":1619508157000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11788911_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540359692","9783540359715"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/11788911_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}