{"id":"https://openalex.org/W4412376974","doi":"https://doi.org/10.1145/3726302.3730048","title":"OmniNER2025: Diverse and Comprehensive Fine-Grained NER Dataset and Benchmark for Chinese","display_name":"OmniNER2025: Diverse and Comprehensive Fine-Grained NER Dataset and Benchmark for Chinese","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376974","doi":"https://doi.org/10.1145/3726302.3730048"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730048","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730048","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730048","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730048","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yong Zhou","orcid":"https://orcid.org/0000-0002-0643-8594"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhou","raw_affiliation_strings":["School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-0643-8594","affiliations":[{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060240389","display_name":"Shuaipeng Liu","orcid":"https://orcid.org/0009-0009-3958-9020"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaipeng Liu","raw_affiliation_strings":["XiaoAI Team, Xiaomi, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3958-9020","affiliations":[{"raw_affiliation_string":"XiaoAI Team, Xiaomi, Beijing, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunqing Li","orcid":"https://orcid.org/0009-0007-0763-9906"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqing Li","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0763-9906","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048141765","display_name":"Mengting Hu","orcid":"https://orcid.org/0000-0003-1536-5400"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengting Hu","raw_affiliation_strings":["College of Software, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1536-5400","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109226513","display_name":"Wen Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Dai","raw_affiliation_strings":["XiaoAI Team, Xiaomi, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2609-5250","affiliations":[{"raw_affiliation_string":"XiaoAI Team, Xiaomi, Beijing, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749133","display_name":"Xiaowei Zhao","orcid":"https://orcid.org/0000-0001-9631-1177"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhao","raw_affiliation_strings":["School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-9631-1177","affiliations":[{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010774945","display_name":"Xiujuan Xu","orcid":"https://orcid.org/0000-0003-4175-4493"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiujuan Xu","raw_affiliation_strings":["School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-4175-4493","affiliations":[{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":null,"issue":null,"first_page":"85","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10028","display_name":"Topic Modeling","score":0.9779000282287598,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.755820631980896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7003008127212524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39643481373786926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3773396611213684},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07658430933952332},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07398936152458191}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.755820631980896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003008127212524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39643481373786926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3773396611213684},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07658430933952332},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07398936152458191}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730048","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730048","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730048","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730048","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730048","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730048","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.7400000095367432,"display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376974.pdf","grobid_xml":"https://content.openalex.org/works/W4412376974.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2163107094","https://openalex.org/W2250709962","https://openalex.org/W2346452181","https://openalex.org/W2567657016","https://openalex.org/W2760505947","https://openalex.org/W2962904552","https://openalex.org/W2964114970","https://openalex.org/W2997200074","https://openalex.org/W3106098584","https://openalex.org/W3169341408","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4385572048","https://openalex.org/W4385572893","https://openalex.org/W4386942538","https://openalex.org/W4393284539"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"As":[0],"Named":[1],"Entity":[2],"Recognition":[3],"(NER)":[4],"tasks":[5],"have":[6,45,178],"evolved,":[7],"artificial":[8],"intelligence":[9],"has":[10],"been":[11],"widely":[12],"applied":[13],"in":[14,31,89,192],"this":[15],"field.":[16],"However,":[17],"most":[18],"benchmarks":[19],"are":[20],"limited":[21],"to":[22,27,37,159],"English,":[23],"making":[24],"it":[25,80],"challenging":[26,103],"replicate":[28],"successful":[29],"experiences":[30],"other":[32],"languages.":[33],"To":[34,77],"expand":[35],"NER":[36,51,87,107,165,181],"informal":[38],"and":[39,71,96,109,118,135,143,155,172,183,190],"diverse":[40,119],"Chinese":[41,50,63,85,106],"text":[42],"scenarios,":[43],"we":[44,127,149,177],"proposed":[46],"a":[47,61],"new":[48],"large-scale":[49],"dataset,":[52,55],"OmniNER2025.":[53],"This":[54,99],"obtained":[56],"from":[57],"user":[58],"posts":[59],"on":[60],"popular":[62],"social":[64],"media":[65],"platform":[66],"Xiaohongshu,":[67],"contains":[68],"195,568":[69],"samples":[70],"89":[72],"categories,":[73],"all":[74],"manually":[75],"annotated.":[76],"our":[78],"knowledge,":[79],"is":[81,101],"currently":[82],"the":[83,129,147,152,161,169,174],"largest":[84],"open-source":[86],"dataset":[88,100,171],"terms":[90],"of":[91,164],"sample":[92,116],"size,":[93],"category":[94],"diversity,":[95],"domain":[97],"coverage.":[98],"more":[102],"than":[104],"existing":[105],"datasets":[108],"better":[110],"reflects":[111],"real-world":[112,193],"applications.":[113],"The":[114],"large":[115],"size":[117],"entity":[120],"types":[121],"provide":[122],"valuable":[123],"research":[124,182],"resources.":[125],"Additionally,":[126],"introduced":[128],"ERRTA":[130,153,175],"tool":[131],"for":[132],"error":[133],"analysis":[134],"teacher":[136],"model":[137,141,185],"guidance,":[138],"significantly":[139],"reducing":[140],"errors":[142],"improving":[144],"performance.":[145],"In":[146],"future,":[148],"will":[150],"refine":[151],"framework":[154],"explore":[156],"optimization":[157],"strategies":[158],"enhance":[160],"practical":[162],"value":[163],"models.":[166],"By":[167],"releasing":[168],"OmniNER2025":[170],"introducing":[173],"tool,":[176],"advanced":[179],"fine-grained":[180],"improved":[184],"performance,":[186],"promoting":[187],"its":[188],"application":[189],"development":[191],"scenarios.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}