{"id":"https://openalex.org/W2006535788","doi":"https://doi.org/10.1109/wi-iat.2010.40","title":"Visual Content Structures for Wrapper Induction in Building Metasearch Systems","display_name":"Visual Content Structures for Wrapper Induction in Building Metasearch Systems","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2006535788","doi":"https://doi.org/10.1109/wi-iat.2010.40","mag":"2006535788"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi-iat.2010.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5112584073","display_name":"Jyh-Jong Tsay","orcid":null},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Jong Tsay","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087261298","display_name":"Chin-Wen Tsay","orcid":null},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Wen Tsay","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626390","display_name":"Xinjie Wang","orcid":"https://orcid.org/0000-0002-9708-1518"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xin-Jie Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.993,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":1,"citation_normalized_percentile":{"value":0.768018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":64,"max":71},"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"183"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9999,"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":0.9999,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9898,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9872,"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/web-crawler","display_name":"Web crawler","score":0.45844033},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.45544812}],"concepts":[{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.9462973},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8062937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76555467},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7508941},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5445904},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.48477024},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4807096},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.45844033},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.45544812},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.41744703},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.30284274}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi-iat.2010.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.47}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W111639511","https://openalex.org/W1489642591","https://openalex.org/W165838864","https://openalex.org/W2013970953","https://openalex.org/W2015551056","https://openalex.org/W2071628657","https://openalex.org/W2102966069","https://openalex.org/W2128341918","https://openalex.org/W2133669904","https://openalex.org/W2134150392","https://openalex.org/W2141814503","https://openalex.org/W2157316480","https://openalex.org/W2160196229","https://openalex.org/W2263765057","https://openalex.org/W4232071090","https://openalex.org/W6578894"],"related_works":["https://openalex.org/W2538203441","https://openalex.org/W2423684479","https://openalex.org/W2406811307","https://openalex.org/W2390587322","https://openalex.org/W2379145789","https://openalex.org/W2363322605","https://openalex.org/W2245375266","https://openalex.org/W2120284761","https://openalex.org/W2103686661","https://openalex.org/W1982433408"],"abstract_inverted_index":{"As":[0],"there":[1],"are":[2,53],"more":[3,5],"and":[4,21,88,114,140,160,191],"online":[6,49,124],"sources":[7,50,94],"available":[8],"on":[9],"the":[10,82,92,101,172],"Web,":[11],"it":[12],"becomes":[13],"very":[14,73],"time-consuming,":[15],"if":[16],"not":[17,60],"impossible,":[18],"to":[19,35,76,86,109],"visit":[20],"search":[22,30,44,68,77,87,189],"all":[23,90,167],"web":[24,64],"sites,":[25],"one":[26,96],"by":[27,66],"one.":[28],"Many":[29],"engines":[31,45,190],"has":[32],"been":[33],"developed":[34],"help":[36],"users":[37,85],"find":[38],"information":[39,93],"of":[40,62,91,100],"their":[41],"need.":[42],"However,":[43],"work":[46],"poor":[47],"for":[48,84,133,183],"whose":[51],"data":[52,116,158,168,184],"often":[54],"in":[55,95,104],"deep":[56,78],"web,":[57],"which":[58,112],"is":[59,71,108],"part":[61],"surface":[63],"indexed":[65],"standard":[67],"engines.":[69],"Metasearch":[70,80],"a":[72,148,163],"popular":[74],"mechanism":[75],"web.":[79],"provides":[81],"capability":[83],"access":[89],"query":[97,119],"submission.":[98],"One":[99],"fundamental":[102],"problems":[103],"building":[105],"metasearch":[106],"systems":[107],"learn":[110],"wrappers":[111],"extract":[113],"integrate":[115],"records":[117,169],"from":[118,123,166,187],"result":[120],"pages":[121],"returned":[122],"sources.":[125],"In":[126],"this":[127],"paper,":[128],"develop":[129],"an":[130],"unsupervised":[131],"approach":[132,145,180],"wrapper":[134],"induction":[135],"that":[136,152,170,178],"combines":[137],"visual,":[138],"content":[139,150,174],"HTML":[141,154],"tag":[142,155,164],"information.":[143],"Our":[144],"first":[146],"learns":[147],"visual":[149,173],"model":[151,165],"alleviates":[153],"differences":[156],"among":[157],"records,":[159],"then":[161],"finds":[162],"match":[171],"model.":[175],"Experiment":[176],"shows":[177],"our":[179],"works":[181],"well":[182],"sets":[185],"collected":[186],"well-known":[188],"shopping":[192],"websites.":[193]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2006535788","counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2024-12-07T19:14:50.849055","created_date":"2016-06-24"}