{"id":"https://openalex.org/W4290875576","doi":"https://doi.org/10.1145/3534678.3539349","title":"Robust and Informative Text Augmentation (RITA) via Constrained Worst-Case Transformations for Low-Resource Named Entity Recognition","display_name":"Robust and Informative Text Augmentation (RITA) via Constrained Worst-Case Transformations for Low-Resource Named Entity Recognition","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875576","doi":"https://doi.org/10.1145/3534678.3539349"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539349","pdf_url":null,"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":null,"license_id":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039891553","display_name":"Hyunwoo Sohn","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyunwoo Sohn","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065070574","display_name":"Baekkwan Park","orcid":"https://orcid.org/0000-0002-0972-5521"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baekkwan Park","raw_affiliation_strings":["The University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"The University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039891553"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.3122,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49830308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1616","last_page":"1624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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":0.8188396692276001},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7702857851982117},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6777985692024231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6627715229988098},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6565098762512207},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.574216365814209},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5465880632400513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4989430904388428},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4729200005531311},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46660348773002625},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.43790918588638306},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4364156126976013},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43436872959136963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4059099853038788},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34826427698135376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188396692276001},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7702857851982117},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6777985692024231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6627715229988098},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6565098762512207},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.574216365814209},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5465880632400513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4989430904388428},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4729200005531311},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46660348773002625},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.43790918588638306},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4364156126976013},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43436872959136963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4059099853038788},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34826427698135376},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539349","pdf_url":null,"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":null,"license_id":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G2094941946","display_name":null,"funder_award_id":"H98230-19-D-0012/0002LAS","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1982982698","https://openalex.org/W2123512824","https://openalex.org/W2476111558","https://openalex.org/W2774162863","https://openalex.org/W2954996726","https://openalex.org/W2998184481","https://openalex.org/W3011411500","https://openalex.org/W3011594683","https://openalex.org/W3035858791","https://openalex.org/W3038098779","https://openalex.org/W3103981637","https://openalex.org/W3105241646","https://openalex.org/W3161492781","https://openalex.org/W3177049011","https://openalex.org/W4252110927","https://openalex.org/W4386847929","https://openalex.org/W6745136726"],"related_works":["https://openalex.org/W2997340383","https://openalex.org/W4309128991","https://openalex.org/W4372259861","https://openalex.org/W4317548404","https://openalex.org/W3022007134","https://openalex.org/W2949671220","https://openalex.org/W2130553454","https://openalex.org/W3022333975","https://openalex.org/W2113853244","https://openalex.org/W2033364610"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,16,117],"deep":[3,21],"learning":[4,22],"have":[5],"brought":[6],"remarkable":[7],"performance":[8,144],"improvements":[9],"named":[11],"entity":[12],"recognition":[13],"(NER),":[14],"specifically":[15],"token-level":[17],"classification":[18],"problems.":[19],"However,":[20],"models":[23],"often":[24],"require":[25],"a":[26,55,73,106,118,140],"large":[27],"amount":[28,142],"of":[29,72,88,91,143,155],"annotated":[30],"data":[31,57,82,93],"to":[32,45,69,104,138],"achieve":[33],"satisfactory":[34],"performance,":[35],"and":[36,42,99,159],"NER":[37],"annotation":[38],"is":[39,135],"significantly":[40],"time-consuming":[41],"labor-intensive":[43],"due":[44],"the":[46,70,85,96,123,148,156],"fine-grained":[47],"labels.":[48],"To":[49,146],"address":[50],"this":[51],"issue,":[52],"we":[53,150],"propose":[54],"textual":[56],"augmentation":[58,129],"method":[59,78,125],"that":[60,122],"can":[61],"automatically":[62],"generate":[63],"informative":[64],"synthetic":[65],"samples,":[66],"which":[67,134],"contribute":[68],"development":[71],"robust":[74,107],"classifier.":[75],"The":[76],"proposed":[77,124],"generates":[79],"additional":[80],"training":[81,92,103],"by":[83],"estimating":[84],"optimal":[86],"level":[87],"worst-case":[89],"transformation":[90],"while":[94],"preserving":[95],"original":[97],"annotation,":[98,133],"includes":[100],"them":[101],"into":[102],"construct":[105],"decision":[108],"boundary.":[109],"Extensive":[110],"experiments":[111],"conducted":[112],"on":[113],"two":[114,127],"benchmark":[115],"datasets":[116],"low-resource":[119],"environment":[120],"reveal":[121],"outperforms":[126],"baseline":[128],"methods":[130],"including":[131],"human":[132],"typically":[136],"considered":[137],"provide":[139],"decent":[141],"boost.":[145],"elucidate":[147],"processes,":[149],"also":[151],"present":[152],"in-depth":[153],"analyses":[154],"generated":[157],"samples":[158],"estimated":[160],"model":[161],"parameters.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}