{"id":"https://openalex.org/W2798955519","doi":"https://doi.org/10.18653/v1/p18-1226","title":"Subword-level Word Vector Representations for Korean","display_name":"Subword-level Word Vector Representations for Korean","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798955519","doi":"https://doi.org/10.18653/v1/p18-1226","mag":"2798955519"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1226","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1226","pdf_url":"https://www.aclweb.org/anthology/P18-1226.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 56th Annual Meeting of the 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/P18-1226.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100679181","display_name":"Sungjoon Park","orcid":"https://orcid.org/0000-0002-1132-9085"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sungjoon Park","raw_affiliation_strings":["Department of Computing, KAIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computing, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054352161","display_name":"Jeongmin Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Byun","raw_affiliation_strings":["Department of Computing, KAIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computing, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067739528","display_name":"Sion Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sion Baek","raw_affiliation_strings":["Program in Cognitive Science, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Program in Cognitive Science, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081838643","display_name":"Yong-Seok Cho","orcid":"https://orcid.org/0000-0002-4851-0128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongseok Cho","raw_affiliation_strings":["Natural Language Processing team, Adecco, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Natural Language Processing team, Adecco, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054771988","display_name":"Alice Oh","orcid":"https://orcid.org/0000-0002-7884-3038"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Alice Oh","raw_affiliation_strings":["Department of Computing, KAIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computing, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100679181"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":4.7387,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.95832376,"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":"2429","last_page":"2438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":1.0,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965999722480774,"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/word2vec","display_name":"Word2vec","score":0.8391200304031372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8175770044326782},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.7577933073043823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7520520687103271},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7171148061752319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.692561149597168},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.657032310962677},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6421191096305847},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4417099356651306},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2741744816303253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09656259417533875}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8391200304031372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175770044326782},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.7577933073043823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7520520687103271},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7171148061752319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.692561149597168},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.657032310962677},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6421191096305847},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4417099356651306},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2741744816303253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09656259417533875},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1226","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1226","pdf_url":"https://www.aclweb.org/anthology/P18-1226.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1226","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1226","pdf_url":"https://www.aclweb.org/anthology/P18-1226.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1446640842","display_name":null,"funder_award_id":"2017-0-01778","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3953289899","display_name":null,"funder_award_id":"2017-0-01778","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798955519.pdf","grobid_xml":"https://content.openalex.org/works/W2798955519.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W638387498","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1938755728","https://openalex.org/W2053921957","https://openalex.org/W2067438047","https://openalex.org/W2117130368","https://openalex.org/W2153579005","https://openalex.org/W2170240176","https://openalex.org/W2176796957","https://openalex.org/W2220350356","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2262907013","https://openalex.org/W2408387521","https://openalex.org/W2419148283","https://openalex.org/W2460442863","https://openalex.org/W2470673105","https://openalex.org/W2493916176","https://openalex.org/W2531207078","https://openalex.org/W2566150155","https://openalex.org/W2604295344","https://openalex.org/W2611767671","https://openalex.org/W2740768945","https://openalex.org/W2759366113","https://openalex.org/W2759998294","https://openalex.org/W2786058094","https://openalex.org/W2950577311","https://openalex.org/W2951559648","https://openalex.org/W2962695106","https://openalex.org/W2962699518","https://openalex.org/W2962732637","https://openalex.org/W2962883855","https://openalex.org/W2963012544","https://openalex.org/W2963099225","https://openalex.org/W2963296402","https://openalex.org/W2964121744","https://openalex.org/W2964234219","https://openalex.org/W4234388646","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2905749112","https://openalex.org/W2346530426","https://openalex.org/W3107848922","https://openalex.org/W3099354896","https://openalex.org/W4287599800","https://openalex.org/W4312264180","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"Research":[0],"on":[1,7,106],"distributed":[2,42],"word":[3,32,43,85],"representations":[4,44],"is":[5],"focused":[6],"widely-used":[8],"languages":[9],"such":[10,121],"as":[11,122],"English.":[12],"Although":[13],"the":[14,27,50,62,66,77],"same":[15],"methods":[16],"can":[17,25],"be":[18],"used":[19],"for":[20,45,84],"other":[21],"languages,":[22],"language-specific":[23],"knowledge":[24,48],"enhance":[26],"accuracy":[28],"and":[29,87,89,103,108,111,114],"richness":[30],"of":[31,54,72],"vector":[33],"representations.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,57,79],"look":[39],"at":[40],"improving":[41],"Korean":[46,59,81],"using":[47],"about":[49],"unique":[51],"linguistic":[52],"structure":[53],"Korean.":[55],"Specifically,":[56],"decompose":[58],"words":[60],"into":[61],"jamo":[63],"level,":[64],"beyond":[65],"characterlevel,":[67],"allowing":[68],"a":[69],"systematic":[70],"use":[71],"subword":[73],"information.":[74],"To":[75],"evaluate":[76],"vectors,":[78],"develop":[80],"test":[82],"sets":[83],"similarity":[86,110],"analogy":[88,112],"make":[90],"them":[91],"publicly":[92],"available.":[93],"The":[94],"results":[95],"show":[96],"that":[97],"our":[98],"simple":[99],"method":[100],"outperforms":[101],"word2vec":[102],"character-level":[104],"Skip-Grams":[105],"semantic":[107],"syntactic":[109],"tasks":[113,120],"contributes":[115],"positively":[116],"toward":[117],"downstream":[118],"NLP":[119],"sentiment":[123],"analysis.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}