{"id":"https://openalex.org/W3022961397","doi":"https://doi.org/10.1007/s10115-022-01767-5","title":"Tailoring and evaluating the Wikipedia for in-domain comparable corpora extraction","display_name":"Tailoring and evaluating the Wikipedia for in-domain comparable corpora extraction","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W3022961397","doi":"https://doi.org/10.1007/s10115-022-01767-5","mag":"3022961397"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-022-01767-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-022-01767-5","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10115-022-01767-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029540488","display_name":"Cristina Espa\u00f1a-Bonet","orcid":"https://orcid.org/0000-0001-5414-4710"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Cristina Espa\u00f1a-Bonet","raw_affiliation_strings":["DFKI GmbH, Saarbr\u00fcken, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Saarbr\u00fcken, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067489760","display_name":"Alberto Barr\u00f3n\u2010Cede\u00f1o","orcid":"https://orcid.org/0000-0003-4719-3420"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Barr\u00f3n-Cede\u00f1o","raw_affiliation_strings":["Universit\u00e0 di Bologna, Forl\u00ec, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Bologna, Forl\u00ec, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103372090","display_name":"Llu\u0131\u0301s M\u00e0rquez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Llu\u00eds M\u00e0rquez","raw_affiliation_strings":["Amazon, AWS AI Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Amazon, AWS AI Labs, Barcelona, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029540488"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.552,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70204826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"65","issue":"3","first_page":"1365","last_page":"1397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129761219024658},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.7692338228225708},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5944696664810181},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5496779084205627},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5279216766357422},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5148698091506958},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49875593185424805},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48418620228767395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4599418342113495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39256173372268677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11663982272148132},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1125122606754303},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.07213014364242554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129761219024658},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.7692338228225708},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5944696664810181},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5496779084205627},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5279216766357422},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5148698091506958},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49875593185424805},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48418620228767395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4599418342113495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39256173372268677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11663982272148132},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1125122606754303},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.07213014364242554},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10115-022-01767-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-022-01767-5","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/903208","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/903208","pdf_url":"https://cris.unibo.it/bitstream/11585/903208/3/Knowledge%20and%20Information%20Systems%20volume%2065%2c%20pages1365%e2%80%931397%20%282023%29.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10115-022-01767-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-022-01767-5","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G4570725529","display_name":null,"funder_award_id":"TIN2012-38523-C02","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W14574270","https://openalex.org/W44018397","https://openalex.org/W58646613","https://openalex.org/W107230253","https://openalex.org/W232456582","https://openalex.org/W316763119","https://openalex.org/W1249771036","https://openalex.org/W1523140216","https://openalex.org/W1598683382","https://openalex.org/W1869906767","https://openalex.org/W1964209958","https://openalex.org/W1966343454","https://openalex.org/W1975879668","https://openalex.org/W1978394996","https://openalex.org/W2000748429","https://openalex.org/W2024244759","https://openalex.org/W2037796960","https://openalex.org/W2047295649","https://openalex.org/W2048957655","https://openalex.org/W2096554363","https://openalex.org/W2098162425","https://openalex.org/W2105673178","https://openalex.org/W2107695330","https://openalex.org/W2119188105","https://openalex.org/W2120779048","https://openalex.org/W2128951443","https://openalex.org/W2131744502","https://openalex.org/W2138166267","https://openalex.org/W2141068210","https://openalex.org/W2147946282","https://openalex.org/W2151521349","https://openalex.org/W2162890210","https://openalex.org/W2164777277","https://openalex.org/W2167265720","https://openalex.org/W2186890008","https://openalex.org/W2250924616","https://openalex.org/W2251597417","https://openalex.org/W2493916176","https://openalex.org/W2529201282","https://openalex.org/W2754727417","https://openalex.org/W2768311607","https://openalex.org/W2803437449","https://openalex.org/W2805790316","https://openalex.org/W2811417394","https://openalex.org/W2924113343","https://openalex.org/W2950485982","https://openalex.org/W2960374072","https://openalex.org/W2963118869","https://openalex.org/W2963341956","https://openalex.org/W2963667932","https://openalex.org/W2973088264","https://openalex.org/W3102617929","https://openalex.org/W3106541240","https://openalex.org/W3130901321","https://openalex.org/W3152788712","https://openalex.org/W3156665996","https://openalex.org/W3197645311","https://openalex.org/W4300780727","https://openalex.org/W6762050013"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W4244686159","https://openalex.org/W3159833212","https://openalex.org/W3010321750","https://openalex.org/W3007654203","https://openalex.org/W3011873497","https://openalex.org/W2186132238","https://openalex.org/W3169620976","https://openalex.org/W2165268584"],"abstract_inverted_index":{"Abstract":[0],"We":[1,40,140],"propose":[2],"a":[3,122,129],"language-independent":[4],"graph-based":[5],"method":[6],"to":[7,44,59,108,133],"build":[8],"\u00e0-la-carte":[9],"article":[10],"collections":[11],"on":[12,23,80,88],"user-defined":[13],"domains":[14],"from":[15],"the":[16,24,27,46,49,99,111,114,135,142,145,148,151],"Wikipedia.":[17],"The":[18],"core":[19],"model":[20,66,86],"is":[21],"based":[22,87],"exploration":[25],"of":[26,48,71,101,113,137,147],"encyclopedia\u2019s":[28],"category":[29],"graph":[30,65],"and":[31,36,55,103,154],"can":[32],"produce":[33],"both":[34],"mono-":[35],"multilingual":[37],"comparable":[38],"collections.":[39,115],"run":[41],"thorough":[42],"experiments":[43],"assess":[45,134],"quality":[47,112,136],"obtained":[50],"corpora":[51],"in":[52],"10":[53],"languages":[54],"743":[56],"domains.":[57],"According":[58],"an":[60,68,84],"extensive":[61],"manual":[62,93],"evaluation,":[63],"our":[64],"reaches":[67],"average":[69],"precision":[70],"$$84\\%$$":[72],"<mml:math":[73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[74],"<mml:mrow>":[75],"<mml:mn>84</mml:mn>":[76],"<mml:mo>%</mml:mo>":[77],"</mml:mrow>":[78],"</mml:math>":[79],"in-domain":[81],"articles,":[82],"outperforming":[83],"alternative":[85,132],"information":[89],"retrieval":[90],"techniques.":[91],"As":[92],"evaluations":[94],"are":[95],"costly,":[96],"we":[97],"introduce":[98],"concept":[100],"domainness":[102,120],"design":[104],"several":[105,155],"automatic":[106,131],"metrics":[107],"account":[109],"for":[110,119],"Our":[116],"best":[117],"metric":[118],"shows":[121],"strong":[123],"correlation":[124],"with":[125,144],"human":[126],"judgments,":[127],"representing":[128],"reasonable":[130],"domain-specific":[138],"corpora.":[139],"release":[141],"toolkit":[143],"implementation":[146],"extraction":[149],"methods,":[150],"evaluation":[152],"measures":[153],"utilities.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
