{"id":"https://openalex.org/W2157160236","doi":"https://doi.org/10.1145/1013367.1013468","title":"Testbed for information extraction from deep web","display_name":"Testbed for information extraction from deep web","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2157160236","doi":"https://doi.org/10.1145/1013367.1013468","mag":"2157160236"},"language":"en","primary_location":{"id":"doi:10.1145/1013367.1013468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2324/2984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082127173","display_name":"Yasuhiro Yamada","orcid":"https://orcid.org/0000-0002-2463-1478"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Yamada","raw_affiliation_strings":["Kyushu Univ. Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Univ. Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["CSIRO Mathematical and Information Sciences Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO Mathematical and Information Sciences Canberra, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079253255","display_name":"Tetsuya Nakatoh","orcid":"https://orcid.org/0000-0001-9299-7757"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Nakatoh","raw_affiliation_strings":["Kyushu Univ. Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Univ. Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006267512","display_name":"Sachio Hirokawa","orcid":"https://orcid.org/0000-0002-8050-1109"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sachio Hirokawa","raw_affiliation_strings":["Kyushu Univ. Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Univ. Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0383,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9442538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"346","last_page":"346"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9584000110626221,"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":0.9505000114440918,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8276343941688538},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.8159990906715393},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6314125061035156},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6055127382278442},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5827394127845764},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5354056358337402},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43674004077911377},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38302427530288696},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.0804850161075592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276343941688538},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.8159990906715393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6314125061035156},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6055127382278442},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5827394127845764},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5354056358337402},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43674004077911377},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38302427530288696},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0804850161075592},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1013367.1013468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01211:0005983975","is_oa":true,"landing_page_url":"https://hdl.handle.net/2324/2984","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc. of the 13th International World Wide Web Conference Alternate Track Papers and Posters","raw_type":"conference paper"},{"id":"pmh:oai:catalog.lib.kyushu-u.ac.jp:2324/2984","is_oa":true,"landing_page_url":"http://hdl.handle.net/2324/2984","pdf_url":"https://catalog.lib.kyushu-u.ac.jp/opac_download_md/2984/www2004.pdf","source":{"id":"https://openalex.org/S4306400832","display_name":"Kyushu University Institutional Repository (QIR) (Kyushu University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I135598925","host_organization_name":"Kyushu University","host_organization_lineage":["https://openalex.org/I135598925"],"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":"Proc. of the 13th International World Wide Web Conference Alternate Track Papers and Posters","raw_type":"conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.7394","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.7394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/nickcr/pubs/yamada_www2004poster.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01211:0005983975","is_oa":true,"landing_page_url":"https://hdl.handle.net/2324/2984","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc. of the 13th International World Wide Web Conference Alternate Track Papers and Posters","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W70990744","https://openalex.org/W100919058","https://openalex.org/W2005646337","https://openalex.org/W2151306141","https://openalex.org/W2301435905"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W3048672182","https://openalex.org/W1509300825","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Search":[0],"results":[1,20,39,85],"generated":[2],"by":[3],"searchable":[4,46],"databases":[5,61,71,79],"are":[6],"served":[7],"dynamically":[8],"and":[9,87,104,112,117,122],"far":[10],"larger":[11],"than":[12],"the":[13,17,27,35,108],"static":[14],"documents":[15],"on":[16,44],"Web.":[18],"These":[19],"pages":[21,40,65],"have":[22,72],"been":[23],"referred":[24],"to":[25,33,41,92],"as":[26],"Deep":[28],"Web":[29],"[1].":[30],"We":[31,48,58,76,95],"need":[32],"extract":[34],"target":[36,90,109],"data":[37],"in":[38,83],"integrate":[42],"them":[43],"different":[45],"databases.":[47],"propose":[49],"a":[50,73,84],"testbed":[51],"for":[52,100,106],"information":[53,91],"extraction":[54,102],"from":[55,63],"search":[56,67],"results.":[57],"chose":[59],"100":[60],"randomly":[62],"114,540":[64],"with":[66],"forms.":[68],"Therefore,":[69],"these":[70],"good":[74],"variety.":[75],"selected":[77],"51":[78],"which":[80],"include":[81],"URLs":[82],"page":[86],"manually":[88],"identify":[89],"be":[93],"extracted.":[94],"also":[96],"suggest":[97],"evaluation":[98,120],"measures":[99],"comparing":[101],"methods":[103,105],"extending":[107],"data.":[110],"Categories":[111],"Subject":[113],"Descriptors":[114],"H.3.4":[115],"[Systems":[116],"Software]:":[118],"Performance":[119],"(efficiency":[121],"effectiveness)":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
