{"id":"https://openalex.org/W2969811512","doi":"https://doi.org/10.1145/3342827.3342846","title":"Evaluation of Morphological Embeddings for the Russian Language","display_name":"Evaluation of Morphological Embeddings for the Russian Language","publication_year":2019,"publication_date":"2019-06-28","ids":{"openalex":"https://openalex.org/W2969811512","doi":"https://doi.org/10.1145/3342827.3342846","mag":"2969811512"},"language":"en","primary_location":{"id":"doi:10.1145/3342827.3342846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342827.3342846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.06628","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077779640","display_name":"Vitaly Romanov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vitaly Romanov","raw_affiliation_strings":["Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025856870","display_name":"Albina Khusainova","orcid":"https://orcid.org/0000-0002-0636-3449"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Albina Khusainova","raw_affiliation_strings":["Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077779640"],"corresponding_institution_ids":["https://openalex.org/I4210116741"],"apc_list":null,"apc_paid":null,"fwci":0.1447,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57839867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","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/T13629","display_name":"Text Readability and Simplification","score":0.9909999966621399,"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/chunking","display_name":"Chunking (psychology)","score":0.8397228121757507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7609277963638306},{"id":"https://openalex.org/keywords/morphology","display_name":"Morphology (biology)","score":0.7498766779899597},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6800576448440552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6440211534500122},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5588353872299194},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5512920618057251},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5163456201553345},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47358018159866333},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4580506384372711},{"id":"https://openalex.org/keywords/russian-language","display_name":"Russian language","score":0.42812249064445496},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36241549253463745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08223918080329895},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0711553692817688}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8397228121757507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609277963638306},{"id":"https://openalex.org/C499950583","wikidata":"https://www.wikidata.org/wiki/Q183252","display_name":"Morphology (biology)","level":2,"score":0.7498766779899597},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6800576448440552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6440211534500122},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5588353872299194},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5512920618057251},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5163456201553345},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47358018159866333},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4580506384372711},{"id":"https://openalex.org/C2993748607","wikidata":"https://www.wikidata.org/wiki/Q7737","display_name":"Russian language","level":2,"score":0.42812249064445496},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36241549253463745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08223918080329895},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0711553692817688},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3342827.3342846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342827.3342846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.06628","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.06628","pdf_url":"https://arxiv.org/pdf/2103.06628","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.06628","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.06628","pdf_url":"https://arxiv.org/pdf/2103.06628","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W309335912","https://openalex.org/W1505680913","https://openalex.org/W1614298861","https://openalex.org/W2142377809","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2417763662","https://openalex.org/W2460442863","https://openalex.org/W2493916176","https://openalex.org/W2512498397","https://openalex.org/W2527945540","https://openalex.org/W2606283965","https://openalex.org/W2606342375","https://openalex.org/W2612560781","https://openalex.org/W2787481916","https://openalex.org/W2807354286","https://openalex.org/W2896457183","https://openalex.org/W2914304175","https://openalex.org/W2950577311","https://openalex.org/W2952230511","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963174553","https://openalex.org/W2964005834","https://openalex.org/W2964144280","https://openalex.org/W4244391100","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2384729545","https://openalex.org/W2198395236","https://openalex.org/W2800417007","https://openalex.org/W147604216","https://openalex.org/W2161080928","https://openalex.org/W2118525872","https://openalex.org/W2279104074","https://openalex.org/W4360764637","https://openalex.org/W2907675665","https://openalex.org/W4286432911"],"abstract_inverted_index":{"A":[0],"number":[1],"of":[2,53,60,85,127],"morphology-based":[3,91],"word":[4,42],"embedding":[5,101],"models":[6],"were":[7],"introduced":[8],"in":[9,50],"recent":[10],"years.":[11],"However,":[12],"their":[13],"evaluation":[14],"was":[15],"mostly":[16,76],"limited":[17],"to":[18,23,36,115],"English,":[19],"which":[20],"is":[21],"known":[22],"be":[24,75],"a":[25,106,128],"morphologically":[26,54],"simple":[27],"language.":[28,57],"In":[29],"this":[30],"paper,":[31],"we":[32],"explore":[33],"whether":[34],"and":[35,67],"what":[37],"extent":[38],"incorporating":[39],"morphology":[40,80,110],"into":[41],"embeddings":[43,92],"improves":[44],"performance":[45,119],"on":[46,120],"downstream":[47],"NLP":[48,58],"tasks,":[49],"the":[51,83,121],"case":[52],"rich":[55],"Russian":[56,71],"tasks":[59,122],"our":[61],"choice":[62],"are":[63],"POS":[64],"tagging,":[65],"Chunking,":[66],"NER":[68],"--":[69,103],"for":[70],"language,":[72],"all":[73],"can":[74],"solved":[77],"using":[78],"only":[79],"without":[81],"understanding":[82,126],"semantics":[84],"words.":[86],"Our":[87],"experiments":[88],"show":[89],"that":[90,123],"trained":[93],"with":[94],"Skipgram":[95],"objective":[96],"do":[97],"not":[98],"outperform":[99],"existing":[100],"model":[102],"FastText.":[104],"Moreover,":[105],"more":[107],"complex,":[108],"but":[109],"unaware":[111],"model,":[112],"BERT,":[113],"allows":[114],"achieve":[116],"significantly":[117],"greater":[118],"presumably":[124],"require":[125],"word's":[129],"morphology.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}