{"id":"https://openalex.org/W3038098779","doi":"https://doi.org/10.1145/3394486.3403149","title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","display_name":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3038098779","doi":"https://doi.org/10.1145/3394486.3403149","mag":"3038098779"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403149","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3394486.3403149","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoming Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Jiang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siawpeng Er","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siawpeng Er","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruijia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijia Wang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tuo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuo Zhao","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":10.1479,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.98541126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1054","last_page":"1064"},"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":0.9976000189781189,"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":0.9782000184059143,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.9334999918937683},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5914999842643738},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.546500027179718},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48829999566078186},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.47040000557899475},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4634000062942505},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4325000047683716}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.9334999918937683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169000148773193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.670199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114000082015991},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5914999842643738},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4325000047683716},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403149","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.15509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.15509","pdf_url":"https://arxiv.org/pdf/2006.15509","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":"doi:10.1145/3394486.3403149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403149","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2004763266","https://openalex.org/W2020978905","https://openalex.org/W2047995599","https://openalex.org/W2079057609","https://openalex.org/W2080133951","https://openalex.org/W2123512824","https://openalex.org/W2143017621","https://openalex.org/W2808481912","https://openalex.org/W2890931111","https://openalex.org/W2891383691","https://openalex.org/W2962739339","https://openalex.org/W2963548348","https://openalex.org/W2964159205","https://openalex.org/W2971071849","https://openalex.org/W3034718094"],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,49,61,75,80,85,89,96,101,106,117,127],"open-domain":[3],"named":[4],"entity":[5],"recognition":[6],"(NER)":[7],"problem":[8],"under":[9],"distant":[10,13,29,90,107],"supervision.":[11],"The":[12,137],"supervision,":[14],"though":[15],"does":[16],"not":[17],"require":[18],"large":[19],"amounts":[20],"of":[21,51,64,129],"manual":[22],"annotations,":[23],"yields":[24],"highly":[25],"incomplete":[26],"and":[27,57,98,109,139],"noisy":[28],"labels":[30],"via":[31],"external":[32],"knowledge":[33],"bases.":[34],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39,68,78,104],"propose":[40,69,110],"a":[41,70,111],"new":[42],"computational":[43],"framework":[44],"--":[45],"BOND,":[46],"which":[47,92],"leverages":[48],"power":[50],"pre-trained":[52,81],"language":[53,82],"models":[54],"(e.g.,":[55],"BERT":[56],"RoBERTa)":[58],"to":[59,84,114],"improve":[60,95,116],"prediction":[62],"performance":[63],"NER":[65,86,135],"models.":[66],"Specifically,":[67],"two-stage":[71],"training":[72],"algorithm:":[73],"In":[74,100],"first":[76],"stage,":[77,103],"adapt":[79],"model":[83,118],"tasks":[87],"using":[88],"labels,":[91,108],"can":[93],"significantly":[94],"recall":[97],"precision;":[99],"second":[102],"drop":[105],"self-training":[112],"approach":[113],"further":[115],"performance.":[119],"Thorough":[120],"experiments":[121],"on":[122],"5":[123],"benchmark":[124],"datasets":[125],"demonstrate":[126],"superiority":[128],"BOND":[130],"over":[131],"existing":[132],"distantly":[133,140],"supervised":[134],"methods.":[136],"code":[138],"labeled":[141],"data":[142],"have":[143],"been":[144],"released":[145],"in":[146],"https://github.com/cliang1453/BOND.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-07-02T00:00:00"}