{"id":"https://openalex.org/W2164239150","doi":"https://doi.org/10.1109/eee.2004.1287353","title":"Data extraction and annotation for dynamic Web pages","display_name":"Data extraction and annotation for dynamic Web pages","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2164239150","doi":"https://doi.org/10.1109/eee.2004.1287353","mag":"2164239150"},"language":"en","primary_location":{"id":"doi:10.1109/eee.2004.1287353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eee.2004.1287353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on e-Technology, e-Commerce and e-Service, 2004. EEE '04. 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011086593","display_name":"Hui Song","orcid":"https://orcid.org/0000-0002-9429-7997"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Song","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102163337","display_name":"Suraj Giri","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suraj Giri","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100845185","display_name":"Fanyuan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanyuan Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011086593"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.7344,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95103504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"499","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8595264554023743},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7068573832511902},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7041150331497192},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6433258056640625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6309194564819336},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.543533205986023},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4991264343261719},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.46862486004829407},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4636491537094116},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.4573184847831726},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4293001592159271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15867599844932556},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.13660961389541626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595264554023743},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7068573832511902},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7041150331497192},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6433258056640625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6309194564819336},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.543533205986023},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4991264343261719},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.46862486004829407},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4636491537094116},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.4573184847831726},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4293001592159271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15867599844932556},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.13660961389541626},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/eee.2004.1287353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eee.2004.1287353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on e-Technology, e-Commerce and e-Service, 2004. EEE '04. 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W102890581","https://openalex.org/W126744842","https://openalex.org/W1532697597","https://openalex.org/W1552303663","https://openalex.org/W1569908913","https://openalex.org/W2051231851","https://openalex.org/W2069388662","https://openalex.org/W2104086170","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2406080254","https://openalex.org/W4233962457","https://openalex.org/W6604188412","https://openalex.org/W6604533964","https://openalex.org/W6675573929"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W2069679074","https://openalex.org/W4239898202","https://openalex.org/W1559090489","https://openalex.org/W3116613346","https://openalex.org/W2115253914","https://openalex.org/W2316185946","https://openalex.org/W2351131669","https://openalex.org/W2368657441","https://openalex.org/W2187545158"],"abstract_inverted_index":{"Many":[0],"Web":[1,41,55],"sites":[2],"contain":[3],"large":[4],"sets":[5],"of":[6,53],"pages":[7,20,42],"generated":[8],"dynamically":[9],"using":[10],"a":[11,31,51],"common":[12],"template.":[13],"The":[14],"structured":[15],"data":[16,37,46,63,67],"extracted":[17,62],"from":[18,39],"these":[19,40],"with":[21],"semantic":[22],"annotation":[23],"are":[24],"valuable":[25],"for":[26],"information":[27],"system.":[28],"We":[29],"proposed":[30],"system,":[32],"ADeaD,":[33],"to":[34],"automatically":[35],"extract":[36],"values":[38],"and":[43,64],"annotate":[44],"the":[45,66],"schema.":[47,68],"Experimental":[48],"evaluation":[49],"on":[50],"lot":[52],"real":[54],"page":[56],"collections":[57],"indicates":[58],"our":[59],"algorithm":[60],"correctly":[61],"annotated":[65]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
