{"id":"https://openalex.org/W2119088569","doi":"https://doi.org/10.1109/icde.2004.1319988","title":"Probe, cluster, and discover: focused extraction of QA-Pagelets from the deep Web","display_name":"Probe, cluster, and discover: focused extraction of QA-Pagelets from the deep Web","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2119088569","doi":"https://doi.org/10.1109/icde.2004.1319988","mag":"2119088569"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1319988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1319988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","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/A5048489384","display_name":"James Caverlee","orcid":"https://orcid.org/0000-0001-8350-8528"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Caverlee","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015530142","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-2037-6860"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Liu","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059372087","display_name":"David Buttler","orcid":"https://orcid.org/0000-0001-7818-715X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Buttler","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048489384"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":16.9569,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98760634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"114"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9817000031471252,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8405848741531372},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666997492313385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6444812417030334},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6348292231559753},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5854110717773438},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5635440349578857},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4751420021057129},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4530588388442993},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44019171595573425},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3928094208240509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3396686613559723},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30573296546936035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13734951615333557},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12813904881477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405848741531372},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666997492313385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6444812417030334},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6348292231559753},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5854110717773438},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5635440349578857},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4751420021057129},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4530588388442993},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44019171595573425},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3928094208240509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3396686613559723},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30573296546936035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13734951615333557},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12813904881477356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2004.1319988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1319988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.5466","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.5466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~caverlee/pubs/caverlee04icde.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320330412","display_name":"Scheme for Promotion of Academic and Research Collaboration","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W151024599","https://openalex.org/W193121434","https://openalex.org/W1574845294","https://openalex.org/W1628571627","https://openalex.org/W1647671624","https://openalex.org/W1651093245","https://openalex.org/W1972645849","https://openalex.org/W1978394996","https://openalex.org/W1987777228","https://openalex.org/W1992419399","https://openalex.org/W1995875735","https://openalex.org/W2020423193","https://openalex.org/W2040075907","https://openalex.org/W2079672501","https://openalex.org/W2091777463","https://openalex.org/W2094930182","https://openalex.org/W2098162425","https://openalex.org/W2100958137","https://openalex.org/W2104086170","https://openalex.org/W2116341550","https://openalex.org/W2119088569","https://openalex.org/W2125725207","https://openalex.org/W2125969310","https://openalex.org/W2131006463","https://openalex.org/W2137845970","https://openalex.org/W2138621811","https://openalex.org/W2150721933","https://openalex.org/W2151626491","https://openalex.org/W2152565070","https://openalex.org/W2165612380","https://openalex.org/W2169852020","https://openalex.org/W2799061466","https://openalex.org/W3139328003","https://openalex.org/W4240407914","https://openalex.org/W4244494905","https://openalex.org/W4247346926","https://openalex.org/W4285719527","https://openalex.org/W6636741502","https://openalex.org/W6637231022","https://openalex.org/W6673311960","https://openalex.org/W6675573929","https://openalex.org/W6677885184","https://openalex.org/W6684779856","https://openalex.org/W6791582515"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"We":[0,21],"introduce":[1],"the":[2,10,36,50,68,85,95],"concept":[3],"of":[4,42,64],"a":[5,14,24,55,79],"QA-Pagelet":[6],"to":[7,9,93],"refer":[8],"content":[11,88],"region":[12],"in":[13],"dynamic":[15],"page":[16,74],"that":[17,83],"contains":[18],"query":[19],"matches.":[20],"present":[22],"THOR,":[23],"scalable":[25],"and":[26,32,87],"efficient":[27],"mining":[28],"system":[29],"for":[30],"discovering":[31],"extracting":[33],"QA-Pagelets":[34],"from":[35,54,72],"deep":[37,56],"Web.":[38],"A":[39],"unique":[40],"feature":[41],"THOR":[43],"is":[44],"its":[45],"two-phase":[46],"extraction":[47],"framework.":[48],"In":[49,67],"first":[51],"phase,":[52,70],"pages":[53,71],"Web":[57],"site":[58],"are":[59,76],"grouped":[60],"into":[61],"distinct":[62],"clusters":[63],"structurally-similar":[65],"pages.":[66],"second":[69],"each":[73],"cluster":[75],"examined":[77],"through":[78],"subtree":[80,91],"filtering":[81],"algorithm":[82],"exploits":[84],"structural":[86],"similarity":[89],"at":[90],"level":[92],"identify":[94],"QA-Pagelets.":[96]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}