{"id":"https://openalex.org/W2759990433","doi":"https://doi.org/10.18653/v1/d17-1267","title":"Identifying Cognate Sets Across Dictionaries of Related Languages","display_name":"Identifying Cognate Sets Across Dictionaries of Related Languages","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2759990433","doi":"https://doi.org/10.18653/v1/d17-1267","mag":"2759990433"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1267","pdf_url":"https://www.aclweb.org/anthology/D17-1267.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1267.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015130382","display_name":"Adam St Arnaud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam St Arnaud","raw_affiliation_strings":["Dept of Computing Science University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computing Science University of Alberta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047802748","display_name":"David Beck","orcid":"https://orcid.org/0000-0001-8422-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Beck","raw_affiliation_strings":["Dept of Linguistics University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Linguistics University of Alberta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008747488","display_name":"Grzegorz Kondrak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grzegorz Kondrak","raw_affiliation_strings":["Dept of Computing Science University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computing Science University of Alberta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5111,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9432692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2519","last_page":"2528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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/T12090","display_name":"Language and cultural evolution","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cognate","display_name":"Cognate","score":0.9939899444580078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979880332946777},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6606356501579285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6605783700942993},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.6280855536460876},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6117876768112183},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6067483425140381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544307291507721},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.46978655457496643},{"id":"https://openalex.org/keywords/co-occurrence","display_name":"Co-occurrence","score":0.4463391602039337},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36518096923828125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0662488341331482}],"concepts":[{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.9939899444580078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979880332946777},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6606356501579285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6605783700942993},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.6280855536460876},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6117876768112183},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6067483425140381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544307291507721},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.46978655457496643},{"id":"https://openalex.org/C154290570","wikidata":"https://www.wikidata.org/wiki/Q1756768","display_name":"Co-occurrence","level":2,"score":0.4463391602039337},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36518096923828125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0662488341331482},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1267","pdf_url":"https://www.aclweb.org/anthology/D17-1267.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1267","pdf_url":"https://www.aclweb.org/anthology/D17-1267.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2759990433.pdf","grobid_xml":"https://content.openalex.org/works/W2759990433.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W28875675","https://openalex.org/W149957658","https://openalex.org/W162855594","https://openalex.org/W168564468","https://openalex.org/W560135136","https://openalex.org/W1518614801","https://openalex.org/W1532325895","https://openalex.org/W1576520375","https://openalex.org/W1590964111","https://openalex.org/W1647671624","https://openalex.org/W1776431790","https://openalex.org/W1965693266","https://openalex.org/W2016156565","https://openalex.org/W2027097848","https://openalex.org/W2072240081","https://openalex.org/W2075149030","https://openalex.org/W2089679262","https://openalex.org/W2096565906","https://openalex.org/W2117717100","https://openalex.org/W2125257703","https://openalex.org/W2125670750","https://openalex.org/W2134639441","https://openalex.org/W2149823587","https://openalex.org/W2153579005","https://openalex.org/W2164998314","https://openalex.org/W2169232192","https://openalex.org/W2229908198","https://openalex.org/W2250547025","https://openalex.org/W2250657762","https://openalex.org/W2251062084","https://openalex.org/W2251111702","https://openalex.org/W2251659274","https://openalex.org/W2295357832","https://openalex.org/W2340681947","https://openalex.org/W2493365355","https://openalex.org/W2511156424","https://openalex.org/W4213258494","https://openalex.org/W4231934124","https://openalex.org/W4294170691","https://openalex.org/W4380767196"],"related_works":["https://openalex.org/W2361693784","https://openalex.org/W2354606016","https://openalex.org/W3149254152","https://openalex.org/W2467647991","https://openalex.org/W4387742703","https://openalex.org/W4381333219","https://openalex.org/W1590512500","https://openalex.org/W2759990433","https://openalex.org/W1161222069","https://openalex.org/W1880786250"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,16,25,61],"system":[3,72],"for":[4],"identifying":[5],"cognate":[6,17,76],"sets":[7,77],"across":[8],"dictionaries":[9],"of":[10,15,24,28,42,75,82],"related":[11],"languages.":[12],"The":[13,46],"likelihood":[14],"relationship":[18],"is":[19],"calculated":[20],"on":[21,66],"the":[22,40,67],"basis":[23],"rich":[26],"set":[27],"features":[29],"that":[30,57],"capture":[31],"both":[32],"phonetic":[33],"and":[34],"semantic":[35],"similarity,":[36],"as":[37,39],"well":[38],"presence":[41],"regular":[43],"sound":[44],"correspondences.":[45],"similarity":[47],"scores":[48],"are":[49],"used":[50],"to":[51],"cluster":[52,80],"words":[53],"from":[54,60],"different":[55],"languages":[56],"may":[58],"originate":[59],"common":[62],"protoword.":[63],"When":[64],"tested":[65],"Algonquian":[68],"language":[69],"family,":[70],"our":[71],"detects":[73],"63%":[74],"while":[78],"maintaining":[79],"purity":[81],"70%.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}