{"id":"https://openalex.org/W2460265413","doi":"https://doi.org/10.18653/v1/n16-3009","title":"Scaling Up Word Clustering","display_name":"Scaling Up Word Clustering","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2460265413","doi":"https://doi.org/10.18653/v1/n16-3009","mag":"2460265413"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n16-3009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3009","pdf_url":"https://www.aclweb.org/anthology/N16-3009.pdf","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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N16-3009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057722634","display_name":"Jon Dehdari","orcid":null},"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"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jon Dehdari","raw_affiliation_strings":["DFKI, Saarbrcken, Germany","University of Saarland, Saarbrcken, Germany","DFKI, Saarbr\u00fccken, Germany","University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI, Saarbrcken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"University of Saarland, Saarbrcken, Germany","institution_ids":["https://openalex.org/I91712215","https://openalex.org/I4210120512"]},{"raw_affiliation_string":"DFKI, Saarbr\u00fccken, Germany","institution_ids":[]},{"raw_affiliation_string":"University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101527631","display_name":"Liling Tan","orcid":"https://orcid.org/0000-0001-7601-903X"},"institutions":[{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Liling Tan","raw_affiliation_strings":["University of Saarland, Saarbrcken, Germany","University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saarland, Saarbrcken, Germany","institution_ids":["https://openalex.org/I91712215","https://openalex.org/I4210120512"]},{"raw_affiliation_string":"University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944"},"institutions":[{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"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":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":["DFKI, Saarbrcken, Germany","University of Saarland, Saarbrcken, Germany","DFKI, Saarbr\u00fccken, Germany","University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI, Saarbrcken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"University of Saarland, Saarbrcken, Germany","institution_ids":["https://openalex.org/I91712215","https://openalex.org/I4210120512"]},{"raw_affiliation_string":"DFKI, Saarbr\u00fccken, Germany","institution_ids":[]},{"raw_affiliation_string":"University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057722634"],"corresponding_institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4210120512","https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":0.8835,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83901312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/perplexity","display_name":"Perplexity","score":0.9024527072906494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8386499881744385},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7304960489273071},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7234750986099243},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7134376168251038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6318645477294922},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5514055490493774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5511884689331055},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5288439989089966},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49846529960632324},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4786749482154846},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.46649739146232605},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3606119751930237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33379286527633667}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9024527072906494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386499881744385},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7304960489273071},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7234750986099243},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7134376168251038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6318645477294922},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5514055490493774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5511884689331055},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5288439989089966},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49846529960632324},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4786749482154846},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.46649739146232605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3606119751930237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33379286527633667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/n16-3009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3009","pdf_url":"https://www.aclweb.org/anthology/N16-3009.pdf","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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:668680","is_oa":true,"landing_page_url":"http://publications.rwth-aachen.de/record/668680","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"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":"NAACL HLT 2016 : The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : Proceedings of the Conference, June 12-17, 2016 San Diego, California, USA<br/>2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016, San Diego, CA, USA, 2016-06-12 - 2016-06-17","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/n16-3009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3009","pdf_url":"https://www.aclweb.org/anthology/N16-3009.pdf","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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2460265413.pdf","grobid_xml":"https://content.openalex.org/works/W2460265413.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W10704533","https://openalex.org/W47415966","https://openalex.org/W130850236","https://openalex.org/W222053410","https://openalex.org/W655994999","https://openalex.org/W1563861331","https://openalex.org/W1614298861","https://openalex.org/W1979102019","https://openalex.org/W2006969979","https://openalex.org/W2100714283","https://openalex.org/W2107038437","https://openalex.org/W2110168585","https://openalex.org/W2113788796","https://openalex.org/W2118584553","https://openalex.org/W2118692229","https://openalex.org/W2121227244","https://openalex.org/W2128634885","https://openalex.org/W2153848201","https://openalex.org/W2158049734","https://openalex.org/W2158139315","https://openalex.org/W2172242228","https://openalex.org/W2250612599","https://openalex.org/W2250907725","https://openalex.org/W2251369387","https://openalex.org/W2296354688","https://openalex.org/W2464630206"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4388926080","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2921174581","https://openalex.org/W2084531783"],"abstract_inverted_index":{"Word":[0],"clusters":[1,83],"improve":[2],"performance":[3],"in":[4,17,92,98,104,114],"many":[5],"NLP":[6],"tasks":[7],"including":[8],"training":[9,106],"neural":[10],"network":[11],"language":[12],"models,":[13],"but":[14],"current":[15],"increases":[16],"datasets":[18],"are":[19],"outpacing":[20],"the":[21,71,109],"ability":[22],"of":[23],"word":[24],"clusterers":[25],"to":[26,78],"handle":[27],"them.":[28],"In":[29],"this":[30,52],"paper":[31],"we":[32],"present":[33],"a":[34,48,84,99],"novel":[35],"bidirectional,":[36],"interpolated,":[37],"refining,":[38],"and":[39,45,120],"alternating":[40],"(BIRA)":[41],"predictive":[42,72],"exchange":[43,73],"algorithm":[44],"introduce":[46],"ClusterCat,":[47],"clusterer":[49],"based":[50],"on":[51],"algorithm.":[53],"We":[54,95],"show":[55],"that":[56],"ClusterCat":[57,82,117],"is":[58,118],"3-85":[59],"times":[60,107],"faster":[61],"than":[62],"four":[63],"other":[64],"well-known":[65],"clusterers,":[66],"while":[67],"also":[68,96],"improving":[69],"upon":[70],"algorithm's":[74],"perplexity":[75],"by":[76],"up":[77],"18%":[79],".":[80],"Notably,":[81],"2.5":[85],"billion":[86],"token":[87],"English":[88],"News":[89],"Crawl":[90],"corpus":[91],"3":[93],"hours.":[94],"evaluate":[97],"machine":[100],"translation":[101,111],"setting,":[102],"resulting":[103],"shorter":[105],"achieving":[108],"same":[110],"quality":[112],"measured":[113],"BLEU":[115],"scores.":[116],"portable":[119],"freely":[121],"available.":[122]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2025-10-10T00:00:00"}