{"id":"https://openalex.org/W2621675718","doi":"https://doi.org/10.18653/v1/e17-1113","title":"Using support vector machines and state-of-the-art algorithms for phonetic alignment to identify cognates in multi-lingual wordlists","display_name":"Using support vector machines and state-of-the-art algorithms for phonetic alignment to identify cognates in multi-lingual wordlists","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2621675718","doi":"https://doi.org/10.18653/v1/e17-1113","mag":"2621675718"},"language":"en","primary_location":{"id":"doi:10.18653/v1/e17-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1113","pdf_url":"https://www.aclweb.org/anthology/E17-1113.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/E17-1113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019358632","display_name":"Gerhard J\u00e4ger","orcid":"https://orcid.org/0000-0002-9642-9359"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"funder","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210161060","display_name":"Max Planck Institute for the Science of Human History","ror":"https://ror.org/05mjrzy91","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210161060"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gerhard J\u00e4ger","raw_affiliation_strings":["Computer-Assisted Language Comparison, Max Planck Institute for the Science of Human History, Max Planck Society"],"affiliations":[{"raw_affiliation_string":"Computer-Assisted Language Comparison, Max Planck Institute for the Science of Human History, Max Planck Society","institution_ids":["https://openalex.org/I4210161060","https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012676548","display_name":"Johann\u2010Mattis List","orcid":"https://orcid.org/0000-0003-2133-8919"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"funder","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210161060","display_name":"Max Planck Institute for the Science of Human History","ror":"https://ror.org/05mjrzy91","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210161060"]},{"id":"https://openalex.org/I4210116870","display_name":"Centre de Recherches Linguistiques sur l'Asie Orientale","ror":"https://ror.org/026h43663","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I162346809","https://openalex.org/I4210116870","https://openalex.org/I4210150854","https://openalex.org/I90669466"]},{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Johann-Mattis List","raw_affiliation_strings":["CRLAO / AIRE EHESS / UPMC PARIS","Computer-Assisted Language Comparison, Max Planck Institute for the Science of Human History, Max Planck Society"],"affiliations":[{"raw_affiliation_string":"CRLAO / AIRE EHESS / UPMC PARIS","institution_ids":["https://openalex.org/I90669466","https://openalex.org/I4210116870"]},{"raw_affiliation_string":"Computer-Assisted Language Comparison, Max Planck Institute for the Science of Human History, Max Planck Society","institution_ids":["https://openalex.org/I4210161060","https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651303","display_name":"Pavel Sofroniev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pavel Sofroniev","raw_affiliation_strings":["Tbingen University Institute of Linguistics Tbingen, Germany","T\u00fcbingen University Institute of Linguistics T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Tbingen University Institute of Linguistics Tbingen, Germany","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"T\u00fcbingen University Institute of Linguistics T\u00fcbingen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019358632"],"corresponding_institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210161060"],"apc_list":null,"apc_paid":null,"fwci":72.7085,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.99835264,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1205","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/T12090","display_name":"Language and cultural evolution","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9868000149726868,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cognate","display_name":"Cognate","score":0.9635913372039795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.73846834897995},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.6747471690177917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.541863203048706},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5278254151344299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5198596119880676},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.496307909488678},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48168835043907166},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4754450023174286},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.4383174479007721},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.41162121295928955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3337318003177643},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28235286474227905},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24440720677375793},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0867571234703064},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08326783776283264}],"concepts":[{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.9635913372039795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73846834897995},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6747471690177917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.541863203048706},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5278254151344299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5198596119880676},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.496307909488678},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48168835043907166},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4754450023174286},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.4383174479007721},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.41162121295928955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3337318003177643},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28235286474227905},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24440720677375793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0867571234703064},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08326783776283264},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/e17-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1113","pdf_url":"https://www.aclweb.org/anthology/E17-1113.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:escidoc.org:escidoc:2418810","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002C-EC45-0","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.18653/v1/e17-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1113","pdf_url":"https://www.aclweb.org/anthology/E17-1113.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G5816191420","display_name":null,"funder_award_id":"DFG-KFG 2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7258815532","display_name":null,"funder_award_id":"KFG 2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2621675718.pdf","grobid_xml":"https://content.openalex.org/works/W2621675718.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W418366875","https://openalex.org/W630710884","https://openalex.org/W655397811","https://openalex.org/W853953785","https://openalex.org/W1574901103","https://openalex.org/W1618905105","https://openalex.org/W1991645955","https://openalex.org/W2009570821","https://openalex.org/W2012690521","https://openalex.org/W2068064057","https://openalex.org/W2074231493","https://openalex.org/W2075149030","https://openalex.org/W2085919111","https://openalex.org/W2089679262","https://openalex.org/W2098524338","https://openalex.org/W2110340112","https://openalex.org/W2115694019","https://openalex.org/W2121564430","https://openalex.org/W2164998314","https://openalex.org/W2229908198","https://openalex.org/W2250657762","https://openalex.org/W2273095374","https://openalex.org/W2291451239","https://openalex.org/W2316904474","https://openalex.org/W2325831267","https://openalex.org/W2340681947","https://openalex.org/W2511156424","https://openalex.org/W2575780413","https://openalex.org/W2581563496","https://openalex.org/W2618067465","https://openalex.org/W2982690190","https://openalex.org/W3214380909","https://openalex.org/W4254240410","https://openalex.org/W4296300796","https://openalex.org/W4298251604"],"related_works":["https://openalex.org/W2356815520","https://openalex.org/W2360457743","https://openalex.org/W4379645529","https://openalex.org/W3009996856","https://openalex.org/W2974737450","https://openalex.org/W2367891843","https://openalex.org/W2369596954","https://openalex.org/W2561203018","https://openalex.org/W106971056","https://openalex.org/W2354606016"],"abstract_inverted_index":{"Most":[0],"current":[1],"approaches":[2],"in":[3,59,74,96],"phylogenetic":[4,57],"linguistics":[5],"require":[6],"as":[7,34,61],"input":[8],"multilingual":[9],"word":[10],"lists":[11],"partitioned":[12],"into":[13],"sets":[14],"of":[15,35,43,56,90,149,161],"etymologically":[16],"related":[17],"words":[18,77],"(cognates).":[19],"Cognate":[20],"identification":[21],"is":[22,30],"so":[23],"far":[24],"done":[25],"manually":[26],"by":[27],"experts,":[28],"which":[29,75],"time":[31],"consuming":[32],"and":[33,82,132,140],"yet":[36],"only":[37],"available":[38],"for":[39,85,129],"a":[40,116,136,145],"small":[41],"number":[42],"well-studied":[44],"language":[45],"families.":[46],"Automatizing":[47],"this":[48],"step":[49],"will":[50],"greatly":[51],"expand":[52],"the":[53,97,158,162],"empirical":[54],"scope":[55],"methods":[58,92,128],"linguistics,":[60],"raw":[62],"wordlists":[63,73],"(in":[64],"phonetic":[65,130],"transcription)":[66],"are":[67,101],"much":[68],"easier":[69],"to":[70,110,124,154,157],"obtain":[71],"than":[72],"cognate":[76,133],"have":[78,93],"been":[79,94],"fully":[80],"identified":[81],"annotated,":[83],"even":[84],"under-studied":[86],"languages.":[87],"A":[88],"couple":[89],"different":[91,126],"proposed":[95],"past,":[98],"but":[99],"they":[100],"either":[102],"disappointing":[103],"regarding":[104],"their":[105],"performance":[106],"or":[107],"not":[108],"applicable":[109],"larger":[111],"datasets.":[112],"Here":[113],"we":[114],"present":[115],"new":[117],"approach":[118],"that":[119],"uses":[120],"support":[121],"vector":[122],"machines":[123],"unify":[125],"state-of-the-art":[127],"alignment":[131],"detection":[134],"within":[135],"single":[137],"framework.":[138],"Training":[139],"evaluating":[141],"these":[142],"method":[143],"on":[144],"typologically":[146],"broad":[147],"collection":[148],"gold-standard":[150],"data":[151],"shows":[152],"it":[153],"be":[155],"superior":[156],"existing":[159],"state":[160],"art.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}