{"id":"https://openalex.org/W2001104490","doi":"https://doi.org/10.1080/08839510701853093","title":"WRAPPER INFERENCE FOR AMBIGUOUS WEB PAGES","display_name":"WRAPPER INFERENCE FOR AMBIGUOUS WEB PAGES","publication_year":2008,"publication_date":"2008-02-06","ids":{"openalex":"https://openalex.org/W2001104490","doi":"https://doi.org/10.1080/08839510701853093","mag":"2001104490"},"language":"en","primary_location":{"id":"doi:10.1080/08839510701853093","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510701853093","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510701853093?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510701853093?needAccess=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Dipartimento di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Roma, Italy","Dipartimento di Informatica e Automazione, Universit\u00e0 degli studi Roma Tre, Roma, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Dipartimento di Informatica e Automazione, Universit\u00e0 degli studi Roma Tre, Roma, Italy#TAB#","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022736687","display_name":"Paolo Merialdo","orcid":"https://orcid.org/0000-0002-3852-8092"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paolo Merialdo","raw_affiliation_strings":["Dipartimento di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Roma, Italy","Dipartimento di Informatica e Automazione, Universit\u00e0 degli studi Roma Tre, Roma, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Dipartimento di Informatica e Automazione, Universit\u00e0 degli studi Roma Tre, Roma, Italy#TAB#","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022736687"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":1.3265,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.8910827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"1-2","first_page":"21","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8534219264984131},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6946765780448914},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6176205277442932},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5974127054214478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4822705388069153},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4757137894630432},{"id":"https://openalex.org/keywords/p","display_name":"P","score":0.46829384565353394},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.44650036096572876},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.42766398191452026},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37697046995162964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3404727876186371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33879587054252625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17357105016708374},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.1519213616847992},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10555875301361084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534219264984131},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6946765780448914},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6176205277442932},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5974127054214478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4822705388069153},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4757137894630432},{"id":"https://openalex.org/C134026603","wikidata":"https://www.wikidata.org/wiki/Q846354","display_name":"P","level":3,"score":0.46829384565353394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44650036096572876},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.42766398191452026},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37697046995162964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3404727876186371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33879587054252625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17357105016708374},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.1519213616847992},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10555875301361084},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1080/08839510701853093","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510701853093","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510701853093?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/118185","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/118185","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.uniroma3.it:11590/148365","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/148365","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:96695","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/96695","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1080/08839510701853093","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510701853093","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510701853093?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2001104490.pdf","grobid_xml":"https://content.openalex.org/works/W2001104490.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1503682011","https://openalex.org/W1519606823","https://openalex.org/W1553229631","https://openalex.org/W1554892943","https://openalex.org/W1602991328","https://openalex.org/W2001341021","https://openalex.org/W2005646337","https://openalex.org/W2051045896","https://openalex.org/W2053524377","https://openalex.org/W2067416210","https://openalex.org/W2072548741","https://openalex.org/W2072936489","https://openalex.org/W2092386826","https://openalex.org/W2093009437","https://openalex.org/W2096496923","https://openalex.org/W2096620925","https://openalex.org/W2104086170","https://openalex.org/W2112546875","https://openalex.org/W2128341918","https://openalex.org/W2134150392","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2154444297","https://openalex.org/W2162340487","https://openalex.org/W2166407869","https://openalex.org/W2170021258","https://openalex.org/W2588668235","https://openalex.org/W6636185090"],"related_works":["https://openalex.org/W1577561363","https://openalex.org/W2148283143","https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2385527937","https://openalex.org/W2005880840","https://openalex.org/W4385305499","https://openalex.org/W3173108628","https://openalex.org/W2507465767","https://openalex.org/W1537820832"],"abstract_inverted_index":{"Several":[0],"studies":[1],"have":[2,36,130,153],"concentrated":[3],"on":[4,148,155],"the":[5,21,51,71,101,104,120,137,142,161,163,169,172],"generation":[6],"of":[7,41,58,94,103,122,165,171],"wrappers":[8,14],"for":[9],"web":[10,60,86,157],"data":[11],"sources.":[12],"As":[13],"can":[15],"be":[16,68],"easily":[17],"described":[18],"as":[19],"grammars,":[20],"grammatical":[22,143],"inference":[23,144],"heritage":[24],"could":[25],"play":[26],"a":[27,38,74,109,131],"significant":[28],"role":[29],"in":[30,55,70,91,114],"this":[31,92,97,127,166],"research":[32],"field.":[33],"Recent":[34],"results":[35,164],"identified":[37],"new":[39],"subclass":[40],"regular":[42],"languages,":[43,47],"called":[44],"prefix":[45,123],"mark-up":[46,124],"that":[48,151],"nicely":[49],"abstract":[50],"structures":[52],"usually":[53],"found":[54],"HTML":[56],"pages":[57,87,113,158],"large":[59],"sites.":[61],"This":[62],"class":[63,93,121],"has":[64,79],"been":[65,80],"proven":[66],"to":[67,111,116,136,159],"identifiable":[69],"limit,":[72],"and":[73,106],"PTIME":[75],"unsupervised":[76],"learning":[77],"algorithm":[78],"previously":[81],"developed.":[82],"Unfortunately,":[83],"many":[84],"real-life":[85,156],"do":[88],"not":[89],"fall":[90],"languages.":[95,125],"In":[96,126],"article":[98],"we":[99,107,129,152],"analyze":[100],"roots":[102],"problem":[105],"propose":[108],"technique":[110],"transform":[112],"order":[115],"bring":[117],"them":[118],"into":[119],"way,":[128],"practical":[132],"solution":[133],"without":[134],"renouncing":[135],"formal":[138],"background":[139],"defined":[140],"within":[141],"framework.":[145],"We":[146],"report":[147],"some":[149],"experiments":[150],"conducted":[154],"evaluate":[160],"approach;":[162],"activity":[167],"demonstrate":[168],"effectiveness":[170],"presented":[173],"techniques.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2016-06-24T00:00:00"}
