{"id":"https://openalex.org/W2025749837","doi":"https://doi.org/10.1145/2187980.2188044","title":"Automatically learning gazetteers from the deep web","display_name":"Automatically learning gazetteers from the deep web","publication_year":2012,"publication_date":"2012-04-16","ids":{"openalex":"https://openalex.org/W2025749837","doi":"https://doi.org/10.1145/2187980.2188044","mag":"2025749837"},"language":"en","primary_location":{"id":"doi:10.1145/2187980.2188044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2188044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113511969","display_name":"Tim Furche","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036346128","display_name":"Giovanni Grasso","orcid":"https://orcid.org/0000-0002-4350-0115"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giovanni Grasso","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008165294","display_name":"Giorgio Orsi","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giorgio Orsi","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051365299","display_name":"Christian Schallhart","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian Schallhart","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101782463","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0003-4699-3557"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"344"},"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/T11719","display_name":"Data Quality and Management","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9550999999046326,"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":0.8102349042892456},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5933630466461182},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5747097134590149},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5690824389457703},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.508927583694458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49473926424980164},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48202574253082275},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47929754853248596},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46133434772491455},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39327991008758545},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14554062485694885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0915900468826294},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06974568963050842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102349042892456},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5933630466461182},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5747097134590149},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5690824389457703},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.508927583694458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49473926424980164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48202574253082275},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47929754853248596},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46133434772491455},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39327991008758545},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14554062485694885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0915900468826294},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06974568963050842},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2187980.2188044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2188044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.6674","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.6674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2012.wwwconference.org/proceedings/companion/p341.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.9615","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.9615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.giovannigrasso.it/wp-content/uploads/2012/02/www-2012-AMBER-Automatically-Learning-Gazetteers-from-the-Deep-Web.pdf","raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:43d19930-da6b-41e8-9d07-90a41f3aa4d1","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:43d19930-da6b-41e8-9d07-90a41f3aa4d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science","raw_type":"Conference item"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:48482079-371d-46cd-8614-6a8e8c439d2c","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:48482079-371d-46cd-8614-6a8e8c439d2c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements at Oxford","raw_type":"Journal article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:e63744a3-ba4f-468f-ac8b-9d4ff0d6adb4","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:e63744a3-ba4f-468f-ac8b-9d4ff0d6adb4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1616576116","https://openalex.org/W2002956097","https://openalex.org/W2035302703","https://openalex.org/W2079594573","https://openalex.org/W2080132606","https://openalex.org/W2133669904","https://openalex.org/W2154444297","https://openalex.org/W2168358004","https://openalex.org/W7062434573"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W4220741973","https://openalex.org/W1185300216","https://openalex.org/W2961085424","https://openalex.org/W2326464900","https://openalex.org/W2096382848","https://openalex.org/W3175996217"],"abstract_inverted_index":{"Wrapper":[0],"induction":[1],"faces":[2],"a":[3,34,60,103,122,153,178,187],"dilemma:":[4],"To":[5,108],"reach":[6],"web":[7,141],"scale,":[8,115],"it":[9],"requires":[10],"automatically":[11,117,168],"generated":[12],"examples,":[13],"but":[14],"to":[15,46,54,69,91,144],"produce":[16],"accurate":[17,155],"results,":[18],"these":[19],"examples":[20],"must":[21],"have":[22],"the":[23,79,83,134,200],"quality":[24],"of":[25,66,82,106,137],"human":[26,171],"annotations.":[27],"We":[28,173],"resolve":[29],"this":[30,86,127,162],"conflict":[31],"with":[32,97,152,170],"AMBER,":[33],"system":[35],"for":[36,180],"fully":[37,167],"automated":[38],"data":[39],"extraction":[40,156],"from":[41,121],"result":[42,142],"pages.":[43],"In":[44,126],"contrast":[45],"previous":[47],"approaches,":[48],"AMBER":[49,88,116,132,176],"employs":[50],"domain":[51,57,119],"specific":[52],"gazetteers":[53,120],"discern":[55],"basic":[56],"attributes":[58,68,72,96],"on":[59,78,102,139,159],"page,":[61],"and":[62,94],"leverages":[63],"repeated":[64,135],"occurrences":[65],"similar":[67],"group":[70],"related":[71],"into":[73],"records":[74,93,138],"rather":[75],"than":[76],"relying":[77],"noisy":[80],"structure":[81,136],"DOM.":[84],"With":[85],"approach":[87,112],"is":[89,149],"able":[90],"identify":[92],"their":[95],"almost":[98],"perfect":[99],"accuracy":[100,194],"(>98%)":[101],"large":[104],"sample":[105,190],"websites.":[107],"make":[109],"such":[110,146],"an":[111],"feasible":[113],"at":[114],"learns":[118],"small":[123,188],"seed":[124,189],"set.":[125],"demonstration,":[128],"we":[129,191],"show":[130,174],"how":[131,175],"uses":[133],"deep":[140],"pages":[143],"learn":[145],"gazetteers.":[147],"This":[148],"only":[150],"possible":[151],"highly":[154],"system.":[157],"Depending":[158],"its":[160],"parametrization,":[161],"learning":[163],"process":[164],"runs":[165],"either":[166],"or":[169],"interaction.":[172],"bootstraps":[177],"gazetteer":[179],"UK":[181,197],"locations":[182,198],"in":[183,195,199],"4":[184],"iterations:":[185],"From":[186],"achieve":[192],"94.4%":[193],"recognizing":[196],"$4th$":[201],"iteration.":[202]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}