{"id":"https://openalex.org/W4392447028","doi":"https://doi.org/10.1145/3639233.3639356","title":"Cross-lingual Text Clustering in a Large System","display_name":"Cross-lingual Text Clustering in a Large System","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4392447028","doi":"https://doi.org/10.1145/3639233.3639356"},"language":"en","primary_location":{"id":"doi:10.1145/3639233.3639356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639356","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639356","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079365638","display_name":"Nicole R. Schneider","orcid":"https://orcid.org/0000-0002-9528-6077"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicole R. Schneider","raw_affiliation_strings":["Computer Science, University of Maryland, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Maryland, United States of America","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050157577","display_name":"Jagan Sankaranarayanan","orcid":"https://orcid.org/0009-0006-0369-816X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagan Sankaranarayanan","raw_affiliation_strings":["Data Infrastructure, Google, United States of America"],"affiliations":[{"raw_affiliation_string":"Data Infrastructure, Google, United States of America","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087437068","display_name":"Hanan Samet","orcid":"https://orcid.org/0000-0001-8230-0653"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanan Samet","raw_affiliation_strings":["Computer Science, University of Maryland, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Maryland, United States of America","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079365638"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.6852,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77182784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9980000257492065,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9980000257492065,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9966999888420105,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8446488380432129},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7813223600387573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5844882130622864},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5171727538108826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.502709150314331},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4368247389793396},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37421655654907227},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.2596481740474701},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.13695207238197327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446488380432129},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7813223600387573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5844882130622864},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5171727538108826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502709150314331},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4368247389793396},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37421655654907227},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.2596481740474701},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.13695207238197327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639233.3639356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639356","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639233.3639356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639356","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1210484973","display_name":null,"funder_award_id":"IIS-18-16889, IIS-20-41415, IIS-21-14451","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2475468242","display_name":null,"funder_award_id":"IIS-20-41415","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3842289071","display_name":null,"funder_award_id":"IIS-21-14451","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392447028.pdf","grobid_xml":"https://content.openalex.org/works/W4392447028.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W33276683","https://openalex.org/W40976687","https://openalex.org/W88302371","https://openalex.org/W1494794415","https://openalex.org/W1509894598","https://openalex.org/W1516414061","https://openalex.org/W1949687736","https://openalex.org/W1970022912","https://openalex.org/W1973312357","https://openalex.org/W1978394996","https://openalex.org/W1991352422","https://openalex.org/W1996764654","https://openalex.org/W1997717003","https://openalex.org/W1998450142","https://openalex.org/W2006685053","https://openalex.org/W2010657328","https://openalex.org/W2013928834","https://openalex.org/W2014615172","https://openalex.org/W2017900763","https://openalex.org/W2020360881","https://openalex.org/W2032115636","https://openalex.org/W2054804336","https://openalex.org/W2059607714","https://openalex.org/W2087323714","https://openalex.org/W2088314245","https://openalex.org/W2102070017","https://openalex.org/W2110443819","https://openalex.org/W2116429057","https://openalex.org/W2120587290","https://openalex.org/W2123171175","https://openalex.org/W2123297508","https://openalex.org/W2123512824","https://openalex.org/W2142255604","https://openalex.org/W2149945051","https://openalex.org/W2157361576","https://openalex.org/W2165612380","https://openalex.org/W2170936641","https://openalex.org/W2390768509","https://openalex.org/W2506991895","https://openalex.org/W2531563875","https://openalex.org/W2733703534","https://openalex.org/W2798389157","https://openalex.org/W2896493177","https://openalex.org/W2954881923","https://openalex.org/W3039695075","https://openalex.org/W3183774761","https://openalex.org/W3215995334","https://openalex.org/W4229912654","https://openalex.org/W4230670993","https://openalex.org/W4238657994","https://openalex.org/W4285168199","https://openalex.org/W4301621477","https://openalex.org/W4397029628"],"related_works":["https://openalex.org/W4224240199","https://openalex.org/W4237592971","https://openalex.org/W2105363053","https://openalex.org/W2899601636","https://openalex.org/W1562544158","https://openalex.org/W2387982377","https://openalex.org/W2143025306","https://openalex.org/W4206655101","https://openalex.org/W2019737068","https://openalex.org/W3015674157"],"abstract_inverted_index":{"The":[0,51],"multilingual":[1,20,36],"world":[2],"needs":[3],"systems":[4],"that":[5,92],"can":[6,22],"cluster":[7,39],"text":[8,21,30],"written":[9,72],"in":[10,31,41,64,73],"multiple":[11],"languages":[12,100],"into":[13],"the":[14,65,102,107,115,124,129,134,139],"same":[15],"thread":[16],"or":[17],"topic.":[18],"Clustering":[19],"be":[23,121],"accomplished":[24],"by":[25,80],"translating":[26],"and":[27,46,53,95,112,133],"then":[28],"clustering":[29,69,116],"a":[32,42,82,89],"canonical":[33],"language,":[34],"using":[35,88],"embeddings":[37],"to":[38,120],"articles":[40,87,97],"shared":[43],"embedding":[44],"space,":[45],"via":[47],"other":[48],"language-independent":[49],"methods.":[50],"performance":[52],"pitfalls":[54],"of":[55,67,85,109,126,131,138],"these":[56,110],"various":[57],"methods":[58],"have":[59],"not":[60],"been":[61],"well":[62],"studied":[63],"context":[66],"real-time":[68],"across":[70],"documents":[71,111],"many":[74],"languages.":[75],"We":[76],"address":[77],"this":[78],"problem":[79],"generating":[81],"large":[83],"dataset":[84],"news":[86],"reference":[90],"architecture":[91],"continuously":[93],"indexed":[94],"clustered":[96],"spanning":[98],"17":[99],"over":[101],"last":[103],"15":[104],"years.":[105],"Through":[106],"analysis":[108],"their":[113],"clusters,":[114],"quality":[117],"is":[118],"shown":[119],"dependent":[122],"on":[123],"normalization":[125],"proper":[127],"nouns,":[128],"types":[130],"georeferences,":[132],"overall":[135],"geographic":[136],"focus":[137],"document.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}