{"id":"https://openalex.org/W2889983522","doi":"https://doi.org/10.18653/v1/d18-1469","title":"Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting","display_name":"Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889983522","doi":"https://doi.org/10.18653/v1/d18-1469","mag":"2889983522"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1469","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1469","pdf_url":"https://www.aclweb.org/anthology/D18-1469.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1469.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084505122","display_name":"Dirk Hovy","orcid":"https://orcid.org/0000-0002-4618-3127"},"institutions":[{"id":"https://openalex.org/I71209653","display_name":"Bocconi University","ror":"https://ror.org/05crjpb27","country_code":"IT","type":"education","lineage":["https://openalex.org/I71209653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dirk Hovy","raw_affiliation_strings":["Bocconi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bocconi University","institution_ids":["https://openalex.org/I71209653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005933561","display_name":"Christoph Purschke","orcid":"https://orcid.org/0000-0002-9655-2058"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Christoph Purschke","raw_affiliation_strings":["University of Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":99.9847,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4383","last_page":"4394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9546999931335449,"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/granularity","display_name":"Granularity","score":0.767949640750885},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.722425639629364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182897925376892},{"id":"https://openalex.org/keywords/retrofitting","display_name":"Retrofitting","score":0.6746054887771606},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5947114825248718},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.587264358997345},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5586192607879639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5055117607116699},{"id":"https://openalex.org/keywords/regional-variation","display_name":"Regional variation","score":0.42121025919914246},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09463325142860413}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.767949640750885},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.722425639629364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182897925376892},{"id":"https://openalex.org/C2778368411","wikidata":"https://www.wikidata.org/wiki/Q24662","display_name":"Retrofitting","level":2,"score":0.6746054887771606},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5947114825248718},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.587264358997345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5586192607879639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055117607116699},{"id":"https://openalex.org/C2776788908","wikidata":"https://www.wikidata.org/wiki/Q3042982","display_name":"Regional variation","level":2,"score":0.42121025919914246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09463325142860413},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d18-1469","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1469","pdf_url":"https://www.aclweb.org/anthology/D18-1469.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/37076","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/37076","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 4383\u20134394 (2018); EMNLP 2018, Brussels, Belgium [BE], 31-10-2018 to 04-11-2018","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1469","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1469","pdf_url":"https://www.aclweb.org/anthology/D18-1469.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889983522.pdf","grobid_xml":"https://content.openalex.org/works/W2889983522.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W609272014","https://openalex.org/W1503259811","https://openalex.org/W1529864641","https://openalex.org/W1541105045","https://openalex.org/W1570098300","https://openalex.org/W1796112755","https://openalex.org/W1973723819","https://openalex.org/W2016381774","https://openalex.org/W2019827344","https://openalex.org/W2026991981","https://openalex.org/W2050038924","https://openalex.org/W2101761627","https://openalex.org/W2102637390","https://openalex.org/W2107251449","https://openalex.org/W2127411301","https://openalex.org/W2131744502","https://openalex.org/W2141277304","https://openalex.org/W2142191319","https://openalex.org/W2142889507","https://openalex.org/W2144364794","https://openalex.org/W2153579005","https://openalex.org/W2158884543","https://openalex.org/W2208556314","https://openalex.org/W2234751941","https://openalex.org/W2251012068","https://openalex.org/W2251157848","https://openalex.org/W2251180427","https://openalex.org/W2251263615","https://openalex.org/W2264054297","https://openalex.org/W2292415828","https://openalex.org/W2397481274","https://openalex.org/W2416513196","https://openalex.org/W2488307822","https://openalex.org/W2548759296","https://openalex.org/W2566957588","https://openalex.org/W2574329320","https://openalex.org/W2591139331","https://openalex.org/W2606131891","https://openalex.org/W2757981529","https://openalex.org/W2783682383","https://openalex.org/W2793186654","https://openalex.org/W2898729163","https://openalex.org/W2962873911","https://openalex.org/W2963514026","https://openalex.org/W2963666326","https://openalex.org/W2963780471","https://openalex.org/W4245436919","https://openalex.org/W4294170691","https://openalex.org/W4298222911","https://openalex.org/W4298826189"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W4251469445","https://openalex.org/W2078531759","https://openalex.org/W2108758729","https://openalex.org/W2011045581","https://openalex.org/W1525624170","https://openalex.org/W4241340851","https://openalex.org/W1528771545","https://openalex.org/W2120612963","https://openalex.org/W2811111905"],"abstract_inverted_index":{"Dialects":[0],"are":[1,27],"one":[2],"of":[3,7,34,42,58,72,112,126,133],"the":[4,32,40,64],"main":[5],"drivers":[6],"language":[8,15],"variation,":[9],"a":[10,24,56,124,147,160],"major":[11],"challenge":[12],"for":[13],"natural":[14],"processing":[16],"tools.":[17],"In":[18],"most":[19],"languages,":[20],"dialects":[21],"exist":[22],"along":[23],"continuum,":[25],"and":[26,47,81,100,136,156],"commonly":[28],"discretized":[29],"by":[30],"combining":[31],"extent":[33],"several":[35],"preselected":[36],"linguistic":[37,79],"variables.":[38],"However,":[39],"selection":[41],"these":[43,115],"variables":[44],"is":[45],"theorydriven":[46],"itself":[48],"insensitive":[49],"to":[50,67,86,91,128,151],"change.":[51],"We":[52],"use":[53],"Doc2Vec":[54],"on":[55],"corpus":[57],"16.8M":[59],"anonymous":[60],"online":[61],"posts":[62],"in":[63],"German-speaking":[65],"area":[66],"learn":[68],"continuous":[69,77],"document":[70],"representations":[71,75],"cities.":[73],"These":[74],"capture":[76],"regional":[78,92,157],"distinctions,":[80],"can":[82],"serve":[83],"as":[84],"input":[85],"downstream":[87],"NLP":[88],"tasks":[89],"sensitive":[90],"variation.":[93],"By":[94],"incorporating":[95],"geographic":[96],"information":[97],"via":[98],"retrofitting":[99,145],"agglomerative":[101],"clustering":[102],"with":[103,144],"structure,":[104],"we":[105,122],"recover":[106],"dialect":[107,120],"areas":[108],"at":[109,159],"various":[110],"levels":[111],"granularity.":[113],"Evaluating":[114],"clusters":[116],"against":[117],"an":[118],"existing":[119],"map,":[121],"achieve":[123],"match":[125],"up":[127],"0.77":[129],"V-score":[130],"(harmonic":[131],"mean":[132],"cluster":[134],"completeness":[135],"homogeneity).":[137],"Our":[138],"results":[139],"show":[140],"that":[141],"representation":[142],"learning":[143],"offers":[146],"robust":[148],"general":[149],"method":[150],"automatically":[152],"expose":[153],"dialectal":[154],"differences":[155],"variation":[158],"finer":[161],"granularity":[162],"than":[163],"was":[164],"previously":[165],"possible.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}