{"id":"https://openalex.org/W4400246244","doi":"https://doi.org/10.1007/s10489-024-05605-9","title":"A large-scale dataset for korean document-level relation extraction from encyclopedia texts","display_name":"A large-scale dataset for korean document-level relation extraction from encyclopedia texts","publication_year":2024,"publication_date":"2024-07-02","ids":{"openalex":"https://openalex.org/W4400246244","doi":"https://doi.org/10.1007/s10489-024-05605-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-05605-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10489-024-05605-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-024-05605-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-024-05605-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031247574","display_name":"Suhyune Son","orcid":"https://orcid.org/0000-0002-5835-5635"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suhyune Son","raw_affiliation_strings":["Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040167127","display_name":"Jungwoo Lim","orcid":"https://orcid.org/0000-0001-8988-2270"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungwoo Lim","raw_affiliation_strings":["Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078410336","display_name":"Seonmin Koo","orcid":"https://orcid.org/0009-0007-8575-2306"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonmin Koo","raw_affiliation_strings":["Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676202","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0002-1587-0389"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327659","display_name":"Young-Hoon Kim","orcid":"https://orcid.org/0000-0003-0265-3825"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younghoon Kim","raw_affiliation_strings":["NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113731463","display_name":"Youngsik Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngsik Lim","raw_affiliation_strings":["NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108378423","display_name":"Dong-Seok Hyun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongseok Hyun","raw_affiliation_strings":["NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER, 5 Jeongjail-ro, Buljeong-ro, Bundang-gu, Seongnam-si, 13561, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033580486","display_name":"Heuiseok Lim","orcid":"https://orcid.org/0000-0002-9269-1157"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Heuiseok Lim","raw_affiliation_strings":["Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9269-1157","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul, 02841, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5033580486"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07460329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"54","issue":"17-18","first_page":"8681","last_page":"8701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9986000061035156,"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":0.9980999827384949,"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":0.882415235042572},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.8311535120010376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6623712778091431},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6313341856002808},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6293424367904663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5590972900390625},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.525301992893219},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5222811698913574},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44005611538887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070599377155304},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.2868363857269287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25928643345832825},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.08204472064971924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.882415235042572},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.8311535120010376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6623712778091431},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6313341856002808},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6293424367904663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5590972900390625},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.525301992893219},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5222811698913574},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44005611538887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070599377155304},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2868363857269287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25928643345832825},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.08204472064971924},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-024-05605-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10489-024-05605-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-024-05605-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10489-024-05605-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s10489-024-05605-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-024-05605-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400246244.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W647480720","https://openalex.org/W1975879668","https://openalex.org/W1981276685","https://openalex.org/W1986768826","https://openalex.org/W2099779943","https://openalex.org/W2759211898","https://openalex.org/W2952179106","https://openalex.org/W2962859618","https://openalex.org/W2963351448","https://openalex.org/W2979826702","https://openalex.org/W3034758281","https://openalex.org/W3093891978","https://openalex.org/W3116122129","https://openalex.org/W3173229273","https://openalex.org/W3204348602","https://openalex.org/W3212766995","https://openalex.org/W4200223488","https://openalex.org/W4221010735","https://openalex.org/W4223491992","https://openalex.org/W4226031465","https://openalex.org/W4281639669","https://openalex.org/W4285305471","https://openalex.org/W4310006738","https://openalex.org/W4322619000","https://openalex.org/W4385571887","https://openalex.org/W4385573294","https://openalex.org/W4389160572","https://openalex.org/W6629967362"],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W2981341912","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W4385734297","https://openalex.org/W4221160509","https://openalex.org/W2547211086","https://openalex.org/W2538200646","https://openalex.org/W2888033806"],"abstract_inverted_index":{"Abstract":[0],"Document-level":[1],"relation":[2],"extraction":[3],"(RE)":[4],"aims":[5],"to":[6,37],"predict":[7],"the":[8,33,38,45,68,85,93,99,104,109,118],"relational":[9],"facts":[10],"between":[11],"two":[12],"given":[13],"entities":[14],"from":[15,62],"a":[16,41],"document.":[17],"Unlike":[18],"widespread":[19],"research":[20,29],"on":[21],"document-level":[22,27,94],"RE":[23,28,95],"in":[24,57],"English,":[25],"Korean":[26,63,105],"is":[30],"still":[31],"at":[32],"very":[34],"beginning":[35],"due":[36],"absence":[39],"of":[40,88],"dataset.":[42],"To":[43],"accelerate":[44],"studies,":[46],"we":[47,91,111],"present":[48],"(":[49],"T":[50],"oward":[51],"Document-Level":[52],"R":[53],"elation":[54],"E":[55],"xtraction":[56],"K":[58],"orean)":[59],"dataset":[60,79],"constructed":[61],"encyclopedia":[64],"documents":[65],"written":[66],"by":[67],"domain":[69],"experts.":[70],"We":[71],"provide":[72],"detailed":[73],"statistical":[74],"analyses":[75],"for":[76],"our":[77,114],"large-scale":[78],"and":[80,120],"human":[81],"evaluation":[82],"results":[83],"suggest":[84],"assured":[86],"quality":[87],".":[89],"Also,":[90],"introduce":[92],"model":[96,116],"that":[97,113],"considers":[98],"named":[100],"entity-type":[101],"while":[102],"considering":[103],"language\u2019s":[106],"properties.":[107],"In":[108],"experiments,":[110],"demonstrate":[112],"proposed":[115],"outperforms":[117],"baselines":[119],"conduct":[121],"qualitative":[122],"analysis.":[123]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}