{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T20:28:19Z","timestamp":1760819299969},"reference-count":30,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2003,4,1]],"date-time":"2003-04-01T00:00:00Z","timestamp":1049155200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Decision Support Systems"],"published-print":{"date-parts":[[2003,4]]},"DOI":"10.1016\/s0167-9236(02)00100-8","type":"journal-article","created":{"date-parts":[[2002,12,28]],"date-time":"2002-12-28T12:34:16Z","timestamp":1041078856000},"page":"129-147","source":"Crossref","is-referenced-by-count":63,"title":["Automatic information extraction from semi-structured Web pages by pattern discovery"],"prefix":"10.1016","volume":"35","author":[{"given":"Chia-Hui","family":"Chang","sequence":"first","affiliation":[]},{"given":"Chun-Nan","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Shao-Cheng","family":"Lui","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/S0167-9236(02)00100-8_BIB1","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/scientificamerican0501-34","article-title":"The semantic web","volume":"284","author":"Berners-Lee","year":"2001","journal-title":"Scientific American"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB2","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1145\/359842.359859","article-title":"A fast string searching algorithm","volume":"20","author":"Boyer","year":"1977","journal-title":"Communications of the ACM"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB3","unstructured":"BrightPlanet.com LLC. The deep web: surfacing hidden value, http:\/\/www.completeplanet.com\/tutorials\/deepweb\/index.asp, July, 2000."},{"key":"10.1016\/S0167-9236(02)00100-8_BIB4","series-title":"Proceedings of the 10th International Conference on World Wide Web, Hong-Kong","first-page":"223","article-title":"IEPAD: information extraction based on pattern discovery","volume":"vol. 2336","author":"Chang","year":"2001"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB5","series-title":"Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Hong Kong, China","first-page":"4","article-title":"Applying pattern mining to web information extraction","author":"Chang","year":"2001"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB6","series-title":"Proceedings of the 10th Meeting of the Information Society of Japan, Tokyo, Japan","first-page":"7","article-title":"The TSIMMIS project: integration of heterogeneous information sources","author":"Chawathe","year":"1994"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB7","series-title":"Proceedings of the 5th International RIAO Conference, Montreal, Quebec, Canada","first-page":"123","article-title":"Towards sophisticated wrapping of Web-based information repositories","author":"Chidlovskii","year":"1997"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB8","series-title":"Proceedings of the 1st International Conference on Web-Age Information Management (WAIM'2000), LNCS Series, Shanghai, China","article-title":"Automatic wrapper generation for web search engines","author":"Chidlovskii","year":"2000"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB9","series-title":"Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Philadelphia, PA, USA","first-page":"50","article-title":"PAT-tree-based keyword extraction for Chinese information retrieval","author":"Chien","year":"1997"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB10","series-title":"Proceedings of the Sixth Message Understanding Conference (MUC-6)","year":"1995"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB11","series-title":"Proceedings of the 1st International Conference on Autonomous Agents, New York, NY, USA","first-page":"39","article-title":"A scalable comparison-shopping agent for the world-wide web","author":"Doorenbos","year":"1997"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB12","series-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD'99), Philadelphia, PA, USA","first-page":"467","article-title":"Record-boundary discovery in web documents","author":"Embley","year":"1999"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB13","series-title":"Information Retrieval: Data Structures and Algorithms","first-page":"66","article-title":"New indices for text: PAT trees and PAT arrays","author":"Gonnet","year":"1992"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB14","series-title":"Database Theory-ICDT '99, 7th International Conference, Proceedings","first-page":"314","article-title":"In search of the lost schema","volume":"vol. 1540","author":"Grumbach","year":"1999"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB15","series-title":"Algorithms on Strings, Trees, and Sequences","author":"Gusfield","year":"1997"},{"issue":"8","key":"10.1016\/S0167-9236(02)00100-8_BIB16","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0306-4379(98)00027-1","article-title":"Generating finite-state transducers for semi-structured data extraction from the web","volume":"23","author":"Hsu","year":"1998","journal-title":"Information Systems"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB17","series-title":"Proceedings of IJCAI-99 Workshop on Text Mining: Foundations, Techniques and Applications, Stockholm, Sweden","first-page":"38","article-title":"Finite-state transducers for semi-structured text mining","author":"Hsu","year":"1999"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB18","series-title":"Proceedings of the 15th National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference, Madison, WI, USA","first-page":"211","article-title":"Modeling web sources for information integration","author":"Knoblock","year":"1998"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB19","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1137\/0206024","article-title":"Fast pattern matching in strings","volume":"6","author":"Knuth","year":"1977","journal-title":"SIAM Journal on Computing"},{"issue":"5","key":"10.1016\/S0167-9236(02)00100-8_BIB20","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1093\/bioinformatics\/15.5.426","article-title":"REPuter: fast computation of maximal repeats in complete genomes","volume":"15","author":"Kurtz","year":"1999","journal-title":"Bioinformatics"},{"issue":"2","key":"10.1016\/S0167-9236(02)00100-8_BIB21","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/5254.757626","article-title":"Gleaning the web","volume":"14","author":"Kushmerick","year":"1999","journal-title":"IEEE Intelligent Systems"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB22","series-title":"Proceedings of the 15th International Joint Conference on Artificial Intelligence (IJCAI '97), Nagoya, Japan","first-page":"729","article-title":"Wrapper induction for information extraction","author":"Kushmerick","year":"1997"},{"issue":"4","key":"10.1016\/S0167-9236(02)00100-8_BIB23","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1145\/321479.321481","article-title":"PATRICIA\u2014practical algorithm to retrieve information coded in alphanumeric","volume":"15","author":"Morrison","year":"1968","journal-title":"Journal of ACM"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB24","series-title":"Proceedings of AAAI'99: Workshop on Machine Learning for Information Extraction","article-title":"Extraction patterns for information extraction tasks: a survey","author":"Muslea","year":"1999"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB25","series-title":"Proceedings of the 3rd International Conference on Autonomous Agents","first-page":"190","article-title":"A hierarchical approach to wrapper induction","author":"Muslea","year":"1999"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB26","series-title":"Proc. of the Fourth Intl. WWW Conference, Boston, USA","article-title":"Multi-Engine Search and Comparison Using the MetaCrawler","author":"Selberg","year":"1995"},{"issue":"1\u20133","key":"10.1016\/S0167-9236(02)00100-8_BIB27","first-page":"233","article-title":"Learning information extraction rules for semi-structured and free text","volume":"34","author":"Soderland","year":"1996","journal-title":"Machine Learning"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB28","unstructured":"The World-Wide Web Consortium (W3C), Extensible markup language (XML), http:\/\/www.w3.org\/XML\/, 1997."},{"issue":"1","key":"10.1016\/S0167-9236(02)00100-8_BIB29","article-title":"Searching the deep web-directed Query engine applications at the department of energy","volume":"7","author":"Warnick","year":"2001","journal-title":"DLib Magazine"},{"key":"10.1016\/S0167-9236(02)00100-8_BIB30","unstructured":"Web Design Group, Wilbur-HTML 3.2, http:\/\/www.htmlhelp.com\/reference\/wilbur\/, 1997."}],"container-title":["Decision Support Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167923602001008?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167923602001008?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,13]],"date-time":"2019-04-13T18:30:04Z","timestamp":1555180204000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167923602001008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,4]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2003,4]]}},"alternative-id":["S0167923602001008"],"URL":"https:\/\/doi.org\/10.1016\/s0167-9236(02)00100-8","relation":{},"ISSN":["0167-9236"],"issn-type":[{"value":"0167-9236","type":"print"}],"subject":[],"published":{"date-parts":[[2003,4]]}}}