{"id":"https://openalex.org/W2213948213","doi":"https://doi.org/10.1613/jair.4780","title":"News Across Languages - Cross-Lingual Document Similarity and Event Tracking","display_name":"News Across Languages - Cross-Lingual Document Similarity and Event Tracking","publication_year":2016,"publication_date":"2016-01-30","ids":{"openalex":"https://openalex.org/W2213948213","doi":"https://doi.org/10.1613/jair.4780","mag":"2213948213"},"language":"en","primary_location":{"id":"doi:10.1613/jair.4780","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.4780","pdf_url":null,"source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1613/jair.4780","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059184495","display_name":"Jan Rupnik","orcid":null},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":true,"raw_author_name":"Jan Rupnik","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084815679","display_name":"Andrej Muhi\u010d","orcid":null},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Andrej Muhic","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032945729","display_name":"Gregor Leban","orcid":"https://orcid.org/0000-0003-1193-5955"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Gregor Leban","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049296186","display_name":"Primo\u017e \u0160kraba","orcid":"https://orcid.org/0000-0002-5300-8984"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Primoz Skraba","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019788602","display_name":"Bla\u017e Fortuna","orcid":"https://orcid.org/0000-0002-8585-9388"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Blaz Fortuna","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043874320","display_name":"Marko Grobelnik","orcid":"https://orcid.org/0000-0001-7373-5591"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Marko Grobelnik","raw_affiliation_strings":["Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Jo\u017eef Stefan Institute, Ljubljana, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059184495"],"corresponding_institution_ids":["https://openalex.org/I3006985408"],"apc_list":null,"apc_paid":null,"fwci":0.8887,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83276223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"55","issue":null,"first_page":"283","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976000189781189,"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":0.802021861076355},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7122251391410828},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6190528273582458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5898033380508423},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5872858762741089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4851608872413635},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45630234479904175},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.44826894998550415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4399985373020172},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07144051790237427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802021861076355},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7122251391410828},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6190528273582458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5898033380508423},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5872858762741089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851608872413635},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45630234479904175},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.44826894998550415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4399985373020172},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07144051790237427},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1613/jair.4780","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.4780","pdf_url":null,"source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1512.07046","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.07046","pdf_url":"https://arxiv.org/pdf/1512.07046","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":"mag:2213948213","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1512.07046.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1512.07046","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1512.07046","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1613/jair.4780","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.4780","pdf_url":null,"source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W58646613","https://openalex.org/W88302371","https://openalex.org/W1502935225","https://openalex.org/W1573481780","https://openalex.org/W1975077471","https://openalex.org/W1978394996","https://openalex.org/W2028776121","https://openalex.org/W2033593667","https://openalex.org/W2045218416","https://openalex.org/W2086320398","https://openalex.org/W2086511124","https://openalex.org/W2100341149","https://openalex.org/W2111068739","https://openalex.org/W2117028099","https://openalex.org/W2117756735","https://openalex.org/W2124807415","https://openalex.org/W2125666396","https://openalex.org/W2135908127","https://openalex.org/W2147152072","https://openalex.org/W2251659877","https://openalex.org/W2398199884","https://openalex.org/W2913066018","https://openalex.org/W2963261555"],"related_works":["https://openalex.org/W2963903800","https://openalex.org/W2951946228","https://openalex.org/W2078323847","https://openalex.org/W2587684062","https://openalex.org/W3100608617","https://openalex.org/W2096276656","https://openalex.org/W2519599384","https://openalex.org/W1711636408","https://openalex.org/W2728069591","https://openalex.org/W2785525924","https://openalex.org/W3093062943","https://openalex.org/W2992507359","https://openalex.org/W2807739445","https://openalex.org/W2564551938","https://openalex.org/W3194958284","https://openalex.org/W2999599192","https://openalex.org/W2982762662","https://openalex.org/W1994500780","https://openalex.org/W3080566208","https://openalex.org/W1996476189"],"abstract_inverted_index":{"In":[0,21],"today's":[1],"world,":[2],"we":[3,24,44,85,113,144],"follow":[4],"news":[5],"which":[6,68,118,156],"is":[7],"distributed":[8],"globally.":[9],"Significant":[10],"events":[11,31],"are":[12,116],"reported":[13],"by":[14],"different":[15,19,56,66,87],"sources":[16],"and":[17,58,78,121,180,186],"in":[18,32,55,65,137],"languages.":[20],"this":[22,49,142],"work,":[23,112],"address":[25],"the":[26,71,100,138,158,167,178,183,187],"problem":[27],"of":[28,30,48,63,80,102,107,152,166,177,182],"tracking":[29],"a":[33,38,75,124,170],"large":[34],"multilingual":[35,76],"stream.":[36],"Within":[37],"recently":[39],"developed":[40],"system":[41,168],"Event":[42],"Registry":[43],"examine":[45],"two":[46,104],"aspects":[47],"problem:":[50],"how":[51,59],"to":[52,60,70,98,149],"compare":[53,86],"articles":[54,64,81,105,128,153],"languages":[57,67,130,155],"link":[61,150],"collections":[62],"refer":[69],"same":[72,159],"event.":[73,160],"Taking":[74],"stream":[77],"clusters":[79,151],"from":[82,129],"each":[83],"language,":[84],"cross-lingual":[88],"document":[89],"similarity":[90,101,126,184],"measures":[91],"based":[92],"on":[93,110],"Wikipedia.":[94],"This":[95],"allows":[96],"us":[97],"compute":[99,123],"any":[103],"regardless":[106],"language.":[108],"Building":[109],"previous":[111],"show":[114],"there":[115],"methods":[117],"scale":[119],"well":[120,173],"can":[122],"meaningful":[125],"between":[127],"with":[131],"little":[132],"or":[133],"no":[134],"direct":[135],"overlap":[136],"training":[139],"data.":[140],"Using":[141],"capability,":[143],"then":[145],"propose":[146],"an":[147,163,175],"approach":[148],"across":[154],"represent":[157],"We":[161],"provide":[162],"extensive":[164],"evaluation":[165,176],"as":[169,172,174],"whole,":[171],"quality":[179],"robustness":[181],"measure":[185],"linking":[188],"algorithm.":[189]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
