{"id":"https://openalex.org/W4281858832","doi":"https://doi.org/10.1145/3534678.3539247","title":"Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition","display_name":"Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4281858832","doi":"https://doi.org/10.1145/3534678.3539247"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539247","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100676456","display_name":"Yinghao Li","orcid":"https://orcid.org/0000-0002-8830-4193"},"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":"Yinghao Li","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102898115","display_name":"Le Song","orcid":"https://orcid.org/0000-0003-0345-9899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Song","raw_affiliation_strings":["BioMap, MBZUAI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMap, MBZUAI, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5316,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9116952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"978","last_page":"988"},"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/T11719","display_name":"Data Quality and Management","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.6951016187667847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6528449058532715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6394610404968262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6350602507591248},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5871222019195557},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.518636167049408},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4972248375415802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4252359867095947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3297434151172638}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6951016187667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528449058532715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6394610404968262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350602507591248},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5871222019195557},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.518636167049408},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4972248375415802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4252359867095947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3297434151172638},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539247","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.14228","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.14228","pdf_url":"https://arxiv.org/pdf/2205.14228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:10.1145/3534678.3539247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539247","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G11240557","display_name":null,"funder_award_id":"MURI N00014-17-1-2656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1726583756","display_name":"III: Small: Go Beyond Short-term Dependency and Homogeneity: A General-Purpose Transformer Recipe for Multi-Domain Heterogeneous Sequential Data Analysis","funder_award_id":"2008334","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4558963220","display_name":null,"funder_award_id":"N00014\u201017\u20101\u20102656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4987246806","display_name":"CAREER: Accelerating Spatial Network Design: An Uncertainty-Driven Predict-and-Optimize Learning Framework","funder_award_id":"2144338","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5397617431","display_name":null,"funder_award_id":"N00014-17-1-2656","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G6484623147","display_name":"III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis","funder_award_id":"2106961","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281858832.pdf","grobid_xml":"https://content.openalex.org/works/W4281858832.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2132679783","https://openalex.org/W2169099542","https://openalex.org/W2251648804","https://openalex.org/W2346452181","https://openalex.org/W2404161646","https://openalex.org/W2740579382","https://openalex.org/W2753034091","https://openalex.org/W2766362701","https://openalex.org/W2769041395","https://openalex.org/W2804766086","https://openalex.org/W2807812398","https://openalex.org/W2889009749","https://openalex.org/W2891383691","https://openalex.org/W2895604144","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2952087486","https://openalex.org/W2959716049","https://openalex.org/W2964140243","https://openalex.org/W2970771982","https://openalex.org/W2997918300","https://openalex.org/W3034718094","https://openalex.org/W3035097673","https://openalex.org/W3092571094","https://openalex.org/W3098507080","https://openalex.org/W3128998556","https://openalex.org/W3156071020","https://openalex.org/W3173471803","https://openalex.org/W3175827219","https://openalex.org/W3176553463","https://openalex.org/W3200496214","https://openalex.org/W4235216760","https://openalex.org/W4287554606"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"named":[2],"entity":[3],"recognition":[4],"methods":[5],"train":[6],"label":[7,30],"models":[8],"to":[9,33,51,104],"aggregate":[10],"the":[11,29,42,46,52,63,73,92,96,105,116,124,145,150,159,162,187],"token":[12],"annotations":[13],"of":[14,54,71,95,126,182],"multiple":[15],"noisy":[16],"labeling":[17],"functions":[18],"(LFs)":[19],"without":[20],"seeing":[21],"any":[22],"manually":[23],"annotated":[24],"labels.":[25],"To":[26,57],"work":[27],"well,":[28],"model":[31,68,151],"needs":[32],"contextually":[34],"identify":[35],"and":[36,148,186],"emphasize":[37],"well-performed":[38],"LFs":[39,47],"while":[40],"down-weighting":[41],"under-performers.":[43],"However,":[44],"evaluating":[45],"is":[48,133,184],"challenging":[49],"due":[50],"lack":[53],"ground":[55],"truths.":[56],"address":[58],"this":[59],"issue,":[60],"we":[61],"propose":[62],"sparse":[64,99],"conditional":[65],"hidden":[66],"Markov":[67],"(Sparse-CHMM).":[69],"Instead":[70],"predicting":[72],"entire":[74],"emission":[75,107,117],"matrix":[76,108],"as":[77,91],"other":[78],"HMM-based":[79],"methods,":[80],"Sparse-CHMM":[81,132,165,183],"focuses":[82],"on":[83,173],"estimating":[84],"its":[85],"diagonal":[86],"elements,":[87],"which":[88,122],"are":[89,101],"considered":[90],"reliability":[93],"scores":[94,100],"LFs.":[97],"The":[98],"then":[102],"expanded":[103],"full-fledged":[106],"with":[109,118,138,158,193],"pre-defined":[110],"expansion":[111],"functions.":[112],"We":[113],"also":[114],"augment":[115],"weighted":[119],"XOR":[120],"scores,":[121],"track":[123],"probabilities":[125],"an":[127],"LF":[128,189,195],"observing":[129],"incorrect":[130],"entities.":[131],"optimized":[134],"through":[135],"unsupervised":[136],"learning":[137],"a":[139,167],"three-stage":[140],"training":[141,146],"pipeline":[142],"that":[143,179],"reduces":[144],"difficulty":[147],"prevents":[149],"from":[152],"falling":[153],"into":[154],"local":[155],"optima.":[156],"Compared":[157],"baselines":[160],"in":[161],"Wrench":[163],"benchmark,":[164],"achieves":[166],"3.01":[168],"average":[169],"F1":[170,196],"score":[171],"improvement":[172],"five":[174],"comprehensive":[175],"datasets.":[176],"Experiments":[177],"show":[178],"each":[180],"component":[181],"effective,":[185],"estimated":[188],"reliabilities":[190],"strongly":[191],"correlate":[192],"true":[194],"scores.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-06-13T00:00:00"}