{"id":"https://openalex.org/W2990405495","doi":"https://doi.org/10.26615/978-954-452-056-4_129","title":"Cross-Family Similarity Learning for Cognate Identification in Low-Resource Languages","display_name":"Cross-Family Similarity Learning for Cognate Identification in Low-Resource Languages","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2990405495","doi":"https://doi.org/10.26615/978-954-452-056-4_129","mag":"2990405495"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_129","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_129","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_129","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077348797","display_name":"Eliel Soisalon-Soininen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliel Soisalon-Soininen","raw_affiliation_strings":["Department of Computer Science University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Helsinki","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088458735","display_name":"Mark Granroth-Wilding","orcid":"https://orcid.org/0000-0002-6020-5687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Granroth-Wilding","raw_affiliation_strings":["Department of Computer Science University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Helsinki","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4338,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73011984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1121","last_page":"1130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7423062324523926},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.7188003063201904},{"id":"https://openalex.org/keywords/cognate","display_name":"Cognate","score":0.706558346748352},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.6792353987693787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6139706969261169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5863759517669678},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5802516937255859},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5605928301811218},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5589752793312073},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5304763913154602},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49299880862236023},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49027231335639954},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4740431308746338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42971518635749817},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41925525665283203},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41590744256973267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1349535882472992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10589703917503357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423062324523926},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.7188003063201904},{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.706558346748352},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.6792353987693787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139706969261169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5863759517669678},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5802516937255859},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5605928301811218},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5589752793312073},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5304763913154602},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49299880862236023},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49027231335639954},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4740431308746338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42971518635749817},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41925525665283203},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41590744256973267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1349535882472992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10589703917503357},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26615/978-954-452-056-4_129","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_129","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_129","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_129","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990405495.pdf","grobid_xml":"https://content.openalex.org/works/W2990405495.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1518614801","https://openalex.org/W1618905105","https://openalex.org/W1647671624","https://openalex.org/W1749856071","https://openalex.org/W1996771106","https://openalex.org/W2012690521","https://openalex.org/W2019689476","https://openalex.org/W2072094567","https://openalex.org/W2077811574","https://openalex.org/W2089679262","https://openalex.org/W2095705004","https://openalex.org/W2096565906","https://openalex.org/W2098524338","https://openalex.org/W2101234009","https://openalex.org/W2117717100","https://openalex.org/W2153635508","https://openalex.org/W2157268555","https://openalex.org/W2157364932","https://openalex.org/W2163993443","https://openalex.org/W2170240176","https://openalex.org/W2176198960","https://openalex.org/W2250657762","https://openalex.org/W2250959792","https://openalex.org/W2251111702","https://openalex.org/W2273095374","https://openalex.org/W2295357832","https://openalex.org/W2340681947","https://openalex.org/W2572149853","https://openalex.org/W2621675718","https://openalex.org/W2759990433","https://openalex.org/W2779833827","https://openalex.org/W2888893419","https://openalex.org/W2903381383","https://openalex.org/W2954254257","https://openalex.org/W2963012544","https://openalex.org/W2979639515","https://openalex.org/W3102831981","https://openalex.org/W3120421331","https://openalex.org/W4298251604"],"related_works":["https://openalex.org/W2361693784","https://openalex.org/W2073096942","https://openalex.org/W2945511280","https://openalex.org/W3149254152","https://openalex.org/W2467647991","https://openalex.org/W2759990433","https://openalex.org/W4387742703","https://openalex.org/W4381333219","https://openalex.org/W1590512500","https://openalex.org/W1161222069"],"abstract_inverted_index":{"We":[0,48,90,117,152],"address":[1],"the":[2,19,22,28,46,50,87,127,130,157,164],"problem":[3],"of":[4,9,12,68,86,144,178,182],"cognate":[5],"identification":[6],"across":[7,149],"vocabularies":[8],"any":[10],"pair":[11],"languages.":[13],"In":[14],"particular,":[15],"we":[16],"focus":[17],"on":[18,120],"case":[20],"where":[21],"examined":[23],"languages":[24,78,85,123],"are":[25],"low-resource,":[26],"to":[27,52,82,139,169,185],"extent":[29,51],"that":[30,126,134,146],"no":[31],"training":[32,54],"data":[33,55,161,184],"whatsoever":[34],"in":[35,76,167],"these":[36],"languages,":[37],"or":[38],"even":[39],"closely":[40],"related":[41],"ones,":[42],"is":[43,136],"available":[44],"for":[45],"task.":[47],"investigate":[49],"which":[53],"from":[56,73,162],"another,":[57],"unrelated":[58],"language":[59,150,165],"family":[60,166],"can":[61,175],"be":[62],"used":[63],"instead.":[64],"Our":[65],"approach":[66],"consists":[67],"learning":[69],"a":[70,97,104,113,179],"similarity":[71],"metric":[72],"example":[74],"cognates":[75],"Indo-European":[77],"and":[79,103,109,124],"applying":[80],"it":[81,135],"low-resource":[83],"Sami":[84,122],"Uralic":[88],"family.":[89],"apply":[91],"two":[92],"models,":[93],"following":[94],"previous":[95],"work:":[96],"Siamese":[98],"convolutional":[99],"neural":[100],"network":[101],"(S-CNN)":[102],"support":[105],"vector":[106],"machine":[107],"(SVM),":[108],"compare":[110],"them":[111],"with":[112,155,160],"Levenshtein":[114],"distance":[115],"baseline.":[116],"test":[118],"performance":[119],"three":[121],"find":[125],"S-CNN":[128,158],"outperforms":[129],"other":[131],"approaches,":[132],"suggesting":[133],"better":[137],"able":[138],"learn":[140],"such":[141],"general":[142],"characteristics":[143],"cognateness":[145],"carry":[147],"over":[148],"families.":[151],"also":[153],"experiment":[154],"fine-tuning":[156],"model":[159,174],"within":[163],"order":[168],"quantify":[170],"how":[171],"well":[172],"this":[173],"make":[176],"use":[177],"small":[180],"amount":[181],"target-domain":[183],"adapt.":[186]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-12-05T00:00:00"}