{"id":"https://openalex.org/W7138269453","doi":"https://doi.org/10.1609/aaai.v40i1.36981","title":"InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling","display_name":"InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138269453","doi":"https://doi.org/10.1609/aaai.v40i1.36981"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i1.36981","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36981","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i1.36981","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054917096","display_name":"Xiaolei Diao","orcid":"https://orcid.org/0000-0002-3269-8103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolei Diao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685940","display_name":"Zhihan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081161227","display_name":"Lida Shi","orcid":"https://orcid.org/0000-0001-5011-6931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lida Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698952","display_name":"Ting Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129665889","display_name":"Ruihua Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruihua Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732881","display_name":"Daqian Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daqian Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129645023","display_name":"Hao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"211","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.2160000056028366,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.2160000056028366,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.11840000003576279,"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":0.07180000096559525,"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/digitization","display_name":"Digitization","score":0.7102000117301941},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4562999904155731},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.42410001158714294},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.412200003862381},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.41190001368522644},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40849998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404000163078308},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7102000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5785999894142151},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4562999904155731},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i1.36981","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36981","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36981","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/36981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.36981","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36981","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8663038611412048}],"awards":[{"id":"https://openalex.org/G1165780893","display_name":null,"funder_award_id":"G3829","funder_id":"https://openalex.org/F4320327282","funder_display_name":"Department of Science and Technology of Jilin Province"},{"id":"https://openalex.org/G1798500827","display_name":null,"funder_award_id":"62476111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4175639196","display_name":null,"funder_award_id":"23VRC033","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund of China"},{"id":"https://openalex.org/G5932415228","display_name":null,"funder_award_id":"2024-JCXK-04","funder_id":"https://openalex.org/F4320322300","funder_display_name":"Jilin University"},{"id":"https://openalex.org/G757758080","display_name":null,"funder_award_id":"20230201086GX","funder_id":"https://openalex.org/F4320327282","funder_display_name":"Department of Science and Technology of Jilin Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322174","display_name":"People's Government of Jilin Province","ror":"https://ror.org/02fzqav45"},{"id":"https://openalex.org/F4320322300","display_name":"Jilin University","ror":"https://ror.org/00js3aw79"},{"id":"https://openalex.org/F4320327282","display_name":"Department of Science and Technology of Jilin Province","ror":null},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Constructing":[0],"historical":[1,29,35,117,174],"language":[2,36,175],"models":[3,163],"(LMs)":[4],"plays":[5],"a":[6,93,120,186],"crucial":[7],"role":[8],"in":[9,82,192],"aiding":[10],"archaeological":[11],"provenance":[12],"studies":[13],"and":[14,59,75,95,107,114,184],"understanding":[15,176],"ancient":[16,63,79,126,142,193],"cultures.":[17],"However,":[18],"existing":[19],"resources":[20],"present":[21],"major":[22],"challenges":[23],"for":[24,122,189],"training":[25],"effective":[26,50],"LMs":[27],"on":[28,43,154,167],"texts.":[30],"First,":[31],"the":[32,55,65,73,130,136,179],"scarcity":[33],"of":[34,62,67,78,116,125,132,181],"samples":[37,148],"renders":[38],"unsupervised":[39],"learning":[40],"approaches":[41],"based":[42],"large":[44],"text":[45],"corpora":[46],"highly":[47],"inefficient,":[48],"hindering":[49],"pre-training.":[51],"Moreover,":[52],"due":[53],"to":[54],"considerable":[56],"temporal":[57],"gap":[58],"complex":[60],"evolution":[61],"scripts,":[64],"absence":[66],"comprehensive":[68],"character":[69,97],"encoding":[70],"schemes":[71],"limits":[72],"digitization":[74,113],"computational":[76],"processing":[77],"texts,":[80,118],"particularly":[81],"early":[83],"Chinese":[84,143,155,194],"writing.":[85],"To":[86,128],"address":[87],"these":[88],"challenges,":[89],"we":[90,134],"introduce":[91],"InteChar,":[92,133],"unified":[94],"extensible":[96],"list":[98],"that":[99,145,162],"integrates":[100],"unencoded":[101],"oracle":[102,156],"bone":[103,157],"characters":[104],"with":[105,149,165],"traditional":[106],"modern":[108],"Chinese.":[109],"InteChar":[110,166],"enables":[111],"consistent":[112],"representation":[115],"providing":[119],"foundation":[121,188],"robust":[123],"modeling":[124],"scripts.":[127],"evaluate":[129],"effectiveness":[131,180],"construct":[135],"Oracle":[137],"Corpus":[138],"Set":[139],"(OracleCS),":[140],"an":[141],"corpus":[144],"combines":[146],"expert-annotated":[147],"LLM-assisted":[150],"data":[151],"augmentation,":[152],"centered":[153],"inscriptions.":[158],"Extensive":[159],"experiments":[160],"show":[161],"trained":[164],"OracleCS":[168],"achieve":[169],"substantial":[170],"improvements":[171],"across":[172],"various":[173],"tasks,":[177],"confirming":[178],"our":[182],"approach":[183],"establishing":[185],"solid":[187],"future":[190],"research":[191],"NLP.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
