{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T05:20:56Z","timestamp":1736054456606,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540285663"},{"type":"electronic","value":"9783540317296"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11546924_68","type":"book-chapter","created":{"date-parts":[[2005,9,27]],"date-time":"2005-09-27T14:09:19Z","timestamp":1127830159000},"page":"696-705","source":"Crossref","is-referenced-by-count":0,"title":["An XML Approach to Semantically Extract Data from HTML Tables"],"prefix":"10.1007","author":[{"given":"Jixue","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyun","family":"Ao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-Hyun","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"68_CR1","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/S0169-023X(01)00016-7","volume":"38","author":"T. Brasethvik","year":"2001","unstructured":"Brasethvik, T., Gulla, J.A.: Natural language analysis for semantic document modeling. DKE\u00a038(1), 45\u201362 (2001)","journal-title":"DKE"},{"key":"68_CR2","unstructured":"Bray, T., Paoli, J., Sperberg-McQueen, C.M.: Extensible markup language (xml) 1.0 (1998), http:\/\/www.w3.org\/TR\/1998\/REC-xml-19980210"},{"key":"68_CR3","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: Towards automatic data extraction from large web sites. In: VLDB, pp. 109\u2013118 (2001)","DOI":"10.1145\/564691.564778"},{"key":"68_CR4","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: automatic data extraction from data-intensive web sites. In: SIGMOD Conference, p. 624 (2002)","DOI":"10.1145\/564691.564778"},{"key":"68_CR5","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P., Missier, P.: An automatic data grabber for large web sites. In: VLDB, pp. 1321\u20131324 (2004)","DOI":"10.1016\/B978-012088469-8.50137-6"},{"key":"68_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/3-540-45816-6_32","volume-title":"Conceptual Modeling - ER 2002","author":"D.W. Embley","year":"2002","unstructured":"Embley, D.W., Tao, C., Liddle, S.W.: Automatically extracting ontologically specified data from html tables of unknown structure. In: Spaccapietra, S., March, S.T., Kambayashi, Y. (eds.) ER 2002. LNCS, vol.\u00a02503, pp. 322\u2013337. Springer, Heidelberg (2002)"},{"key":"68_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1007\/3-540-47961-9_53","volume-title":"Advanced Information Systems Engineering","author":"I.M.R.E. Filha","year":"2002","unstructured":"Filha, I.M.R.E., da Silva, A.S., Laender, A.H.F., Embley, D.W.: Using nested tables for representing and querying semistructured web data. In: Pidduck, A.B., Mylopoulos, J., Woo, C.C., Ozsu, M.T. (eds.) CAiSE 2002. LNCS, vol.\u00a02348, pp. 719\u2013723. Springer, Heidelberg (2002)"},{"key":"68_CR8","unstructured":"Hammer, J., Garcia-Molina, H., Cho, J., Aranha, R., Crespo, A.: Extracting semistructured information from the web. In: Proceedings of the Workshop on Management of Semistructured Data (1997)"},{"key":"68_CR9","unstructured":"HTML-Working-Group. Hypertext markup language (html), W3C (2004), http:\/\/www.w3.org\/MarkUp\/"},{"key":"68_CR10","doi-asserted-by":"crossref","unstructured":"Lam, W., Lin, W.-Y.: Learning to extract hierarchical information from semi-structured documents. In: CIKM, pp. 250\u2013257 (2000)","DOI":"10.1145\/354756.354826"},{"key":"68_CR11","doi-asserted-by":"crossref","unstructured":"Lerman, K., Getoor, L., Minton, S., Knoblock, C.A.: Using the structure of web sites for automatic segmentation of tables. In: SIGMOD Conference, pp. 119\u2013130 (2004)","DOI":"10.1145\/1007568.1007584"},{"key":"68_CR12","unstructured":"Lerman, K., Knoblock, C.A., Minton, S.: Automatic data extraction from lists and tables in web sources. In: Automatic Text Extraction and Mining workshop (ATEM 2001), IJCAI 2001, Seattle, WA (2001), http:\/\/www.isi.edu\/~lerman\/papers\/lerman-atem2001.pdf"},{"key":"68_CR13","doi-asserted-by":"crossref","unstructured":"Lim, S.-J., Nag, Y.-K.: An automated approach for retrieving hierarchical data from html tables. In: CIKM, pp. 466\u2013474 (1999)","DOI":"10.1145\/319950.320052"},{"key":"68_CR14","unstructured":"Soderland, S.: Learning to extract text-based information from the world wide web. In: KDD, pp. 251\u2013254 (1997)"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11546924_68.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T15:45:23Z","timestamp":1736005523000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11546924_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540285663","9783540317296"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/11546924_68","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}