{"id":"https://openalex.org/W4386365860","doi":"https://doi.org/10.18293/seke2023-128","title":"BDC:Using BERT and Deep Clustering to Improve Chinese Proper Noun Recognition","display_name":"BDC:Using BERT and Deep Clustering to Improve Chinese Proper Noun Recognition","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4386365860","doi":"https://doi.org/10.18293/seke2023-128"},"language":"en","primary_location":{"id":"doi:10.18293/seke2023-128","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2023-128","pdf_url":"https://doi.org/10.18293/seke2023-128","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2023-128","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112506857","display_name":"Yuanchi Ma","orcid":"https://orcid.org/0000-0003-4220-6317"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchi Ma","raw_affiliation_strings":["Beijing Institute of Technology","Beijing Institute of Technology Institute of Engineering Medicine beijing,China","School of Computer Science and Technology beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology Institute of Engineering Medicine beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Computer Science and Technology beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101769679","display_name":"Hui He","orcid":"https://orcid.org/0000-0002-1437-8069"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui He","raw_affiliation_strings":["School of Computer Science and Technology beijing,China","Beijing Institute of Technology","Beijing Institute of Technology Institute of Engineering Medicine beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology beijing,China","institution_ids":[]},{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology Institute of Engineering Medicine beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082774439","display_name":"Zhendong Niu","orcid":"https://orcid.org/0000-0002-0576-7572"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhendong Niu","raw_affiliation_strings":["School of Computer Science and Technology beijing,China","Beijing Institute of Technology","Beijing Institute of Technology Institute of Engineering Medicine beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology beijing,China","institution_ids":[]},{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology Institute of Engineering Medicine beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082774439"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.1725,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56393696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2023","issue":null,"first_page":"57","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9921000003814697,"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":0.8285174369812012},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7649929523468018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7455326318740845},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7307074069976807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7137841582298279},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5841509103775024},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.583560049533844},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5090134143829346},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5011813640594482},{"id":"https://openalex.org/keywords/proper-noun","display_name":"Proper noun","score":0.49463149905204773},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4601472318172455},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4498898983001709},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4384940266609192},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4255583882331848},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3807666003704071},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10838758945465088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08274361491203308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285174369812012},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7649929523468018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7455326318740845},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7307074069976807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7137841582298279},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5841509103775024},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.583560049533844},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5090134143829346},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5011813640594482},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.49463149905204773},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4601472318172455},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4498898983001709},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4384940266609192},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4255583882331848},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3807666003704071},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10838758945465088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08274361491203308},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2023-128","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2023-128","pdf_url":"https://doi.org/10.18293/seke2023-128","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2023-128","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2023-128","pdf_url":"https://doi.org/10.18293/seke2023-128","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8023270376","display_name":null,"funder_award_id":"62272048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386365860.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1582260546","https://openalex.org/W1614298861","https://openalex.org/W1967350923","https://openalex.org/W1987971958","https://openalex.org/W2061883799","https://openalex.org/W2131726681","https://openalex.org/W2147880316","https://openalex.org/W2250999640","https://openalex.org/W2295030615","https://openalex.org/W2557672990","https://openalex.org/W2567657016","https://openalex.org/W2604737827","https://openalex.org/W2762995374","https://openalex.org/W2888597024","https://openalex.org/W2896457183","https://openalex.org/W2938179091","https://openalex.org/W2962902328","https://openalex.org/W2963548348","https://openalex.org/W2964727037","https://openalex.org/W2970323499","https://openalex.org/W2977664641","https://openalex.org/W2979826702","https://openalex.org/W2990204573","https://openalex.org/W3035642486","https://openalex.org/W3048241244","https://openalex.org/W3089797352","https://openalex.org/W3091998909","https://openalex.org/W3104774463","https://openalex.org/W3117559572","https://openalex.org/W3174142642","https://openalex.org/W3198155159","https://openalex.org/W3210120707","https://openalex.org/W4214745526","https://openalex.org/W4224324845","https://openalex.org/W4225513420","https://openalex.org/W4284690666","https://openalex.org/W4312433216","https://openalex.org/W4379510236","https://openalex.org/W6681236446","https://openalex.org/W6766378161","https://openalex.org/W6767179725","https://openalex.org/W6785909547","https://openalex.org/W6802852670"],"related_works":["https://openalex.org/W3118607722","https://openalex.org/W2803492476","https://openalex.org/W924436176","https://openalex.org/W1524602228","https://openalex.org/W4206326973","https://openalex.org/W2919547998","https://openalex.org/W2943690567","https://openalex.org/W2549028007","https://openalex.org/W1979321383","https://openalex.org/W2357925437"],"abstract_inverted_index":{"Proper":[0],"noun":[1,81],"recognition":[2],"is":[3,20,85,139],"a":[4,37,95],"sub-task":[5],"in":[6,40,145],"named":[7],"entity":[8],"recognition.However,":[9],"few":[10],"methods":[11,28],"have":[12,121],"been":[13],"specifically":[14],"applied":[15],"to":[16,45,77,86,101,112],"the":[17,24,41,46,52,56,88,107,114,126,137,147],"Chinese.The":[18],"reason":[19],"that":[21],"most":[22],"of":[23,51,58,116,142],"existing":[25],"deep":[26,109],"clustering":[27,110],"rely":[29],"on":[30,125],"manually":[31],"labeled":[32],"training":[33],"sets,":[34],"which":[35],"take":[36],"long":[38],"time":[39],"learning":[42],"process.And":[43],"due":[44],"wide":[47],"and":[48,55,129,136,149],"large-scale":[49],"nature":[50],"proprietary":[53],"domain":[54],"lack":[57],"word":[59,89,98,103],"boundaries,":[60],"recognizing":[61],"Chinese":[62,79],"specialized":[63],"terms":[64],"from":[65,119],"unstructured":[66],"text":[67],"remains":[68],"challenging.In":[69],"this":[70],"paper,":[71],"we":[72,105],"design":[73],"an":[74,140],"unsupervised":[75],"method":[76,100,111,144],"improve":[78],"proper":[80,117],"recognition.The":[82],"first":[83],"step":[84],"implement":[87],"separation":[90],"for":[91],"Chinese,":[92],"followed":[93],"by":[94],"BERT-based":[96],"improved":[97],"characterization":[99],"obtain":[102],"vectors.Finally,":[104],"use":[106],"autoencoder-based":[108],"complete":[113],"extraction":[115],"nouns":[118],"books.We":[120],"done":[122],"comparison":[123],"experiments":[124],"public":[127],"dataset":[128],"our":[130,143],"selected":[131],"professional":[132],"book":[133],"data":[134],"respectively,":[135],"result":[138],"improvement":[141],"both":[146],"accuracy":[148],"F1":[150],"values.":[151],"1":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}