{"id":"https://openalex.org/W4320024174","doi":"https://doi.org/10.1109/bigdata55660.2022.10020462","title":"Crosslingual Section Title Alignment in Wikipedia","display_name":"Crosslingual Section Title Alignment in Wikipedia","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024174","doi":"https://doi.org/10.1109/bigdata55660.2022.10020462"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020462","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5088762737","display_name":"Djellel Difallah","orcid":"https://orcid.org/0000-0002-7513-6047"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Djellel Difallah","raw_affiliation_strings":["NYU Abu Dhabi,Abu Dhabi,UAE","NYU Abu Dhabi, Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"NYU Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042104049","display_name":"Diego S\u00e1ez-Trumper","orcid":"https://orcid.org/0000-0002-7679-5423"},"institutions":[{"id":"https://openalex.org/I4210126245","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Saez-Trumper","raw_affiliation_strings":["Wikimedia Foundation,Barcelona,Spain","Wikimedia Foundation, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Wikimedia Foundation,Barcelona,Spain","institution_ids":["https://openalex.org/I4210126245"]},{"raw_affiliation_string":"Wikimedia Foundation, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046658632","display_name":"Eriq Augustine","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eriq Augustine","raw_affiliation_strings":["UC. Santa Cruz,California,USA","UC. Santa Cruz, California, USA"],"affiliations":[{"raw_affiliation_string":"UC. Santa Cruz,California,USA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"UC. Santa Cruz, California, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101446790","display_name":"Robert West","orcid":"https://orcid.org/0000-0002-3984-1232"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Robert West","raw_affiliation_strings":["EPFL,Lausanne,Switzerland","EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"EPFL,Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037525426","display_name":"Leila Zia","orcid":"https://orcid.org/0000-0001-7005-8759"},"institutions":[{"id":"https://openalex.org/I4210126245","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leila Zia","raw_affiliation_strings":["Wikimedia Foundation,California,USA","Wikimedia Foundation, California, USA"],"affiliations":[{"raw_affiliation_string":"Wikimedia Foundation,California,USA","institution_ids":["https://openalex.org/I4210126245"]},{"raw_affiliation_string":"Wikimedia Foundation, California, USA","institution_ids":["https://openalex.org/I4210126245"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088762737"],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54304029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5892","last_page":"5901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9922000169754028,"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":0.8625856637954712},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.788263201713562},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6202752590179443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6041263937950134},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5847267508506775},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5601410269737244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5038620829582214},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4824657738208771},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.46180835366249084},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4216322898864746},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.41249457001686096},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24496063590049744},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10324519872665405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625856637954712},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.788263201713562},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6202752590179443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6041263937950134},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5847267508506775},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5601410269737244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038620829582214},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4824657738208771},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.46180835366249084},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4216322898864746},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41249457001686096},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24496063590049744},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10324519872665405},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020462","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W588062613","https://openalex.org/W1542713999","https://openalex.org/W1942169943","https://openalex.org/W1950900001","https://openalex.org/W2006969979","https://openalex.org/W2056748234","https://openalex.org/W2070493638","https://openalex.org/W2080133951","https://openalex.org/W2119188105","https://openalex.org/W2126725946","https://openalex.org/W2157331557","https://openalex.org/W2158418361","https://openalex.org/W2171450492","https://openalex.org/W2252721148","https://openalex.org/W2296307963","https://openalex.org/W2406488743","https://openalex.org/W2460082991","https://openalex.org/W2558395983","https://openalex.org/W2561995736","https://openalex.org/W2587972260","https://openalex.org/W2797253696","https://openalex.org/W2952190837","https://openalex.org/W2954222332","https://openalex.org/W2963572185","https://openalex.org/W2964263523","https://openalex.org/W3102374157","https://openalex.org/W3154075676","https://openalex.org/W3210975017","https://openalex.org/W4239476440","https://openalex.org/W4299579390","https://openalex.org/W4318147677","https://openalex.org/W6617458402","https://openalex.org/W6632702419","https://openalex.org/W6638588478","https://openalex.org/W6640722844","https://openalex.org/W6652311901","https://openalex.org/W6679155404","https://openalex.org/W6713842036","https://openalex.org/W6718547200","https://openalex.org/W6734787708","https://openalex.org/W6765510844","https://openalex.org/W6983471262"],"related_works":["https://openalex.org/W1585034923","https://openalex.org/W3107474891","https://openalex.org/W2435130738","https://openalex.org/W1592339875","https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W2250526968","https://openalex.org/W1484029852","https://openalex.org/W1697423248","https://openalex.org/W2757332886"],"abstract_inverted_index":{"Sections":[0],"are":[1,9],"the":[2,18,54,97,101,157,170,191,211],"building":[3],"blocks":[4],"of":[5,20,32,49,58,83,103,120,159,190,210],"Wikipedia":[6,44,108],"articles.":[7],"They":[8],"used":[10],"by":[11,91],"editors":[12],"to":[13,124,168,201,205,219],"create":[14],"a":[15,50,74,81,87,112,135,149],"structure":[16],"for":[17,86,115,153],"content":[19,145],"articles,":[21],"which":[22],"in":[23,38,187,208],"turn":[24],"improves":[25],"reading":[26],"and":[27,56,110,207],"editing":[28],"workflows.":[29],"Today,":[30],"millions":[31],"carefully":[33],"curated":[34],"section":[35,59,84,105,125,144,174],"titles":[36,60,85,106,126],"exist":[37],"more":[39,212],"than":[40,183],"160":[41],"actively":[42],"edited":[43],"languages":[45,62,109,215],"as":[46,68,199,217],"standalone":[47],"components":[48],"larger":[51],"system.":[52],"Understanding":[53],"connection":[55],"correspondence":[57],"across":[61,107],"presents":[63],"various":[64],"application":[65],"opportunities":[66],"such":[67,117,198,216],"article":[69],"template":[70],"recommendation,":[71],"i.e.,":[72],"given":[73],"source":[75],"language":[76,192,196],"article,":[77],"we":[78,133,163],"can":[79],"generate":[80,129],"skeleton":[82],"target":[88],"language.":[89],"Inspired":[90],"this":[92,154],"real-world":[93],"data":[94],"mining":[95],"problem,":[96],"present":[98],"paper":[99],"introduces":[100],"problem":[102],"aligning":[104],"proposes":[111],"probabilistic":[113],"method":[114],"identifying":[116],"correspondences.":[118],"Instead":[119],"applying":[121],"translation":[122,185],"tools":[123],"(which":[127],"may":[128],"out-of":[130],"lexicon":[131],"titles),":[132],"develop":[134],"supervised":[136],"model":[137,169],"that":[138,178],"identifies":[139],"cross-language":[140],"mappings":[141,197],"based":[142],"on":[143],"features.":[146],"We":[147,176],"collected":[148],"ground-truth":[150],"dataset":[151],"created":[152],"purpose":[155],"with":[156],"help":[158],"volunteers.":[160],"In":[161],"addition,":[162],"use":[164],"Probabilistic":[165],"Soft":[166],"Logic":[167],"dependencies":[171],"between":[172],"multilingual":[173],"pairings.":[175],"show":[177],"our":[179],"approach":[180],"performs":[181],"better":[182],"machine":[184],"solutions":[186],"about":[188],"80%":[189],"pairs,":[193],"including":[194],"distant":[195],"Arabic":[200],"Russian":[202],"or":[203],"French":[204,218],"Japanese":[206],"many":[209],"closely":[213],"related":[214],"Spanish.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}