{"id":"https://openalex.org/W3153665856","doi":"https://doi.org/10.1145/3404835.3462994","title":"Predicting Links on Wikipedia with Anchor Text Information","display_name":"Predicting Links on Wikipedia with Anchor Text Information","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153665856","doi":"https://doi.org/10.1145/3404835.3462994","mag":"3153665856"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.11734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Robin Brochier","orcid":null},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Robin Brochier","raw_affiliation_strings":["Aix Marseille Universit\u00e9, Universit\u00e9 de Toulon, Marseille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix Marseille Universit\u00e9, Universit\u00e9 de Toulon, Marseille, France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I21491767"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fr\u00e9d\u00e9ric B\u00e9chet","orcid":null},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric B\u00e9chet","raw_affiliation_strings":["Aix Marseille Universit\u00e9, Universit\u00e9 de Toulon, Marseille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix Marseille Universit\u00e9, Universit\u00e9 de Toulon, Marseille, France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I21491767"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1758","last_page":"1762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9718000292778015,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9495999813079834,"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/key","display_name":"Key (lock)","score":0.6588000059127808},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5231000185012817},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3569999933242798},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821000218391418},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6588000059127808},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5379999876022339},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2689000070095062}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3404835.3462994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.11734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11734","pdf_url":"https://arxiv.org/pdf/2105.11734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:HAL:hal-03233373v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03233373","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, New York, France. &#x27E8;10.1145/3404835.3462994&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.11734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11734","pdf_url":"https://arxiv.org/pdf/2105.11734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1512583955","display_name":"INITIATIVE D'EXCELLENCE AIX MARSEILLE UNIVERSITE","funder_award_id":"ANR-11-IDEX-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3969625138","display_name":"ILCB: Institute of Language Communication and the Brain","funder_award_id":"ANR-16-CONV-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4866930200","display_name":null,"funder_award_id":"ANR-11-IDEX","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5208230211","display_name":"Multimedia archives enhancement: multimodal machine comprehension of language for new intelligent interfaces of scientific and cultural mediation","funder_award_id":"ANR-19-CE38-0011","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7527776872","display_name":null,"funder_award_id":"11-IDEX-0001-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G782245399","display_name":null,"funder_award_id":"IDEX-0001-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7929012186","display_name":null,"funder_award_id":"ANR-11-IDEX-0001-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1501299699","https://openalex.org/W1755289444","https://openalex.org/W2091019377","https://openalex.org/W2138621811","https://openalex.org/W2146304342","https://openalex.org/W2147152072","https://openalex.org/W2154851992","https://openalex.org/W2162630660","https://openalex.org/W2168190036","https://openalex.org/W2296235651","https://openalex.org/W2740934577","https://openalex.org/W2799179950","https://openalex.org/W2914688415","https://openalex.org/W2962756421","https://openalex.org/W2999817249","https://openalex.org/W3017057548","https://openalex.org/W3085747564"],"related_works":[],"abstract_inverted_index":{"Wikipedia,":[0],"the":[1,19,32,52,57,68,87,90,100,138,142],"largest":[2],"open-collaborative":[3],"online":[4],"encyclopedia,":[5],"is":[6],"a":[7,23,41,65,134],"corpus":[8],"of":[9,22,40,64,70,93,99,137,141],"documents":[10],"bound":[11],"together":[12],"by":[13,47],"internal":[14],"hyperlinks.":[15],"These":[16],"links":[17],"form":[18],"building":[20],"blocks":[21],"large":[24],"network":[25],"whose":[26],"structure":[27],"contains":[28],"important":[29],"information":[30],"on":[31,96,112],"concepts":[33],"covered":[34],"in":[35,51],"this":[36,83],"encyclopedia.":[37],"The":[38],"presence":[39],"link":[42,94],"between":[43],"two":[44],"articles,":[45],"materialised":[46],"an":[48,118],"anchor":[49,113],"text":[50,114],"source":[53],"page":[54],"pointing":[55],"to":[56,76],"target":[58],"page,":[59],"can":[60],"increase":[61],"readers'":[62],"understanding":[63],"topic.":[66],"However,":[67],"process":[69],"linking":[71,110],"follows":[72],"specific":[73],"editorial":[74],"rules":[75],"avoid":[77],"both":[78],"under-linking":[79],"and":[80,89,103,123],"over-linking.":[81],"In":[82],"paper,":[84],"we":[85,128],"study":[86],"transductive":[88],"inductive":[91],"tasks":[92],"prediction":[95],"several":[97,125],"subsets":[98],"English":[101],"Wikipedia":[102],"identify":[104],"some":[105],"key":[106],"challenges":[107],"behind":[108],"automatic":[109],"based":[111],"information.":[115],"We":[116],"propose":[117,129],"appropriate":[119],"evaluation":[120],"sampling":[121],"methodology":[122],"compare":[124],"algorithms.":[126],"Moreover,":[127],"baseline":[130],"models":[131],"that":[132],"provide":[133],"good":[135],"estimation":[136],"overall":[139],"difficulty":[140],"tasks.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-04-26T00:00:00"}
