{"id":"https://openalex.org/W2144502291","doi":"https://doi.org/10.1109/bigdata.2015.7363931","title":"Mining local gazetteers of literary Chinese with CRF and pattern based methods for biographical information in Chinese history","display_name":"Mining local gazetteers of literary Chinese with CRF and pattern based methods for biographical information in Chinese history","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2144502291","doi":"https://doi.org/10.1109/bigdata.2015.7363931","mag":"2144502291"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1511.01556","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005169817","display_name":"Chao-Lin Liu","orcid":"https://orcid.org/0000-0002-4093-1497"},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chao-Lin Liu","raw_affiliation_strings":["Graduate Institute of Linguistics, National Chengchi University, Taiwan","Dept. of Computer Science, National Chengchi University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Linguistics, National Chengchi University, Taiwan","institution_ids":["https://openalex.org/I87354575"]},{"raw_affiliation_string":"Dept. of Computer Science, National Chengchi University, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790190","display_name":"Chih-Kai Huang","orcid":"https://orcid.org/0000-0002-2282-5893"},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Kai Huang","raw_affiliation_strings":["Department of Computer Science, National Chengchi University, Taiwan","Dept. of Computer Science, National Chengchi University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chengchi University, Taiwan","institution_ids":["https://openalex.org/I87354575"]},{"raw_affiliation_string":"Dept. of Computer Science, National Chengchi University, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035865925","display_name":"Hongsu Wang","orcid":"https://orcid.org/0000-0002-1840-2046"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongsu Wang","raw_affiliation_strings":["Institute for Quantitative Social Science, Harvard University, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Quantitative Social Science, Harvard University, USA","institution_ids":["https://openalex.org/I4210098931","https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027908099","display_name":"Peter K. Bol","orcid":"https://orcid.org/0000-0002-1485-095X"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter K. Bol","raw_affiliation_strings":["Institute for Quantitative Social Science, Harvard University, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Quantitative Social Science, Harvard University, USA","institution_ids":["https://openalex.org/I4210098931","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005169817"],"corresponding_institution_ids":["https://openalex.org/I87354575"],"apc_list":null,"apc_paid":null,"fwci":0.8932,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83061487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1629","last_page":"1638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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/T11719","display_name":"Data Quality and Management","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7507739067077637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6476646065711975},{"id":"https://openalex.org/keywords/china","display_name":"China","score":0.5857647061347961},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5666179060935974},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.538780152797699},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4766205847263336},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.46723824739456177},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42189908027648926},{"id":"https://openalex.org/keywords/history-of-china","display_name":"History of China","score":0.41975805163383484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3340698778629303},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26800960302352905},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.2639496326446533},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.1316308081150055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1019778847694397}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7507739067077637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6476646065711975},{"id":"https://openalex.org/C191935318","wikidata":"https://www.wikidata.org/wiki/Q148","display_name":"China","level":2,"score":0.5857647061347961},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5666179060935974},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.538780152797699},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4766205847263336},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.46723824739456177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42189908027648926},{"id":"https://openalex.org/C119795817","wikidata":"https://www.wikidata.org/wiki/Q82972","display_name":"History of China","level":3,"score":0.41975805163383484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3340698778629303},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26800960302352905},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2639496326446533},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.1316308081150055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1019778847694397},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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:10.1109/bigdata.2015.7363931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1511.01556","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1511.01556","pdf_url":"https://arxiv.org/pdf/1511.01556","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:1511.01556","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1511.01556","pdf_url":"https://arxiv.org/pdf/1511.01556","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W137097415","https://openalex.org/W199416282","https://openalex.org/W2020278455","https://openalex.org/W2028455051","https://openalex.org/W2053681556","https://openalex.org/W2101210369","https://openalex.org/W2120437191","https://openalex.org/W2129999749","https://openalex.org/W2138433202","https://openalex.org/W2140016149","https://openalex.org/W2244504482","https://openalex.org/W2403732399","https://openalex.org/W2485630019","https://openalex.org/W2528594257","https://openalex.org/W2794553132","https://openalex.org/W2886244784","https://openalex.org/W4206192903","https://openalex.org/W6605578442","https://openalex.org/W6657423403","https://openalex.org/W6664020577","https://openalex.org/W6713138956","https://openalex.org/W6728438967","https://openalex.org/W6749398588","https://openalex.org/W6754303401"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2347460059","https://openalex.org/W2111726165","https://openalex.org/W2886890203","https://openalex.org/W3080906831","https://openalex.org/W2388050078"],"abstract_inverted_index":{"Person":[0],"names":[1,4,115,129],"and":[2,12,46,50,85,116,145,153],"location":[3],"are":[5],"essential":[6],"building":[7],"blocks":[8],"for":[9,40],"identifying":[10],"events":[11],"social":[13],"networks":[14],"in":[15,21,37,59,98,101,136],"historical":[16,41,60],"documents":[17],"that":[18,68,91],"were":[19,64,69,118],"written":[20],"literary":[22,38],"Chinese.":[23],"We":[24],"take":[25],"the":[26,30,56,86,121,127,131,137],"lead":[27],"to":[28,54,159],"explore":[29],"research":[31],"on":[32,109],"algorithmically":[33],"recognizing":[34],"named":[35],"entities":[36],"Chinese":[39,102],"studies":[42],"with":[43,66],"language-model":[44],"based":[45,48],"conditional-random-field":[47],"methods,":[49],"extend":[51],"our":[52],"work":[53],"mining":[55],"document":[57],"structures":[58],"documents.":[61],"Practical":[62],"evaluations":[63],"conducted":[65],"texts":[67],"extracted":[70,128],"from":[71,120],"more":[72],"than":[73],"220":[74],"volumes":[75],"of":[76,114,126,142],"local":[77,99],"gazetteers":[78],"(Difangzhi,":[79],"$$$).":[80],"Difangzhi":[81],"is":[82],"a":[83],"huge":[84],"single":[87],"most":[88],"important":[89],"collection":[90],"contains":[92],"information":[93,133],"about":[94],"officers":[95],"who":[96],"served":[97],"government":[100],"history.":[103],"Our":[104],"methods":[105],"performed":[106],"very":[107],"well":[108],"these":[110],"realistic":[111],"tests.":[112],"Thousands":[113],"addresses":[117],"identified":[119],"texts.":[122],"A":[123],"good":[124],"portion":[125],"match":[130],"biographical":[132],"currently":[134],"recorded":[135],"China":[138],"Biographical":[139],"Database":[140],"(CBDB)":[141],"Harvard":[143],"University,":[144],"many":[146],"others":[147],"can":[148],"be":[149],"verified":[150],"by":[151],"historians":[152],"will":[154],"become":[155],"as":[156],"new":[157],"additions":[158],"CBDB.":[160],"<sup":[161],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}