{"id":"https://openalex.org/W3094999800","doi":"https://doi.org/10.1162/tacl_a_00350","title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","display_name":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3094999800","doi":"https://doi.org/10.1162/tacl_a_00350","mag":"3094999800"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00350","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00350","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00350/1924263/tacl_a_00350.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00350/1924263/tacl_a_00350.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073858017","display_name":"Aditi Chaudhary","orcid":"https://orcid.org/0009-0002-4658-4040"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditi Chaudhary","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Department of Computer Science, George Mason University","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111476836","display_name":"Zaid Sheikh","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Sheikh","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","#N#George Mason University#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"#N#George Mason University#N#","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01004665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","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/T12072","display_name":"Machine Learning and Algorithms","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122738599777222},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7109895944595337},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6748716831207275},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6138949990272522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5545178055763245},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5346630811691284},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5117197036743164},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49531975388526917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4826924800872803},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.42060330510139465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4173600673675537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09370139241218567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122738599777222},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7109895944595337},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6748716831207275},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6138949990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5545178055763245},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5346630811691284},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5117197036743164},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49531975388526917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4826924800872803},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.42060330510139465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4173600673675537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09370139241218567},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00350","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00350","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00350/1924263/tacl_a_00350.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.00767","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.00767","pdf_url":"https://arxiv.org/pdf/2011.00767","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":"","raw_type":"text"},{"id":"mag:3094999800","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.00767","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:98d044bf96054b06aa494cf3d95b90fa","is_oa":true,"landing_page_url":"https://doaj.org/article/98d044bf96054b06aa494cf3d95b90fa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 9, Pp 1-16 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2011.00767","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.00767","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00350","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00350","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00350/1924263/tacl_a_00350.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2016630033","https://openalex.org/W2074064986","https://openalex.org/W2135890475","https://openalex.org/W2142523187","https://openalex.org/W2153962014","https://openalex.org/W2161044106","https://openalex.org/W2165484066","https://openalex.org/W2168199177","https://openalex.org/W2171671120","https://openalex.org/W2252069213","https://openalex.org/W2282396980","https://openalex.org/W2296283641","https://openalex.org/W2550821151","https://openalex.org/W2626778328","https://openalex.org/W2785232118","https://openalex.org/W2805736358","https://openalex.org/W2891602716","https://openalex.org/W2895891096","https://openalex.org/W2903158431","https://openalex.org/W2927062526","https://openalex.org/W2933254221","https://openalex.org/W2949840430","https://openalex.org/W2950938254","https://openalex.org/W2952233506","https://openalex.org/W2962702662","https://openalex.org/W2963336393","https://openalex.org/W2963341956","https://openalex.org/W2963377948","https://openalex.org/W2963902936","https://openalex.org/W2964085249","https://openalex.org/W2970913210","https://openalex.org/W2998653650"],"related_works":["https://openalex.org/W3129479925","https://openalex.org/W2905382854","https://openalex.org/W3205180534","https://openalex.org/W3201408086","https://openalex.org/W817877629","https://openalex.org/W2325684928","https://openalex.org/W2908944636","https://openalex.org/W2997960807","https://openalex.org/W2970457158","https://openalex.org/W3021728680","https://openalex.org/W3205088081","https://openalex.org/W2887561352","https://openalex.org/W3009165395","https://openalex.org/W2499171197","https://openalex.org/W3011654523","https://openalex.org/W3103425602","https://openalex.org/W2773549337","https://openalex.org/W3016074070","https://openalex.org/W2181320390","https://openalex.org/W3085342743"],"abstract_inverted_index":{"Active":[0],"learning":[1],"(AL)":[2],"uses":[3],"a":[4,55,145],"data":[5,182],"selection":[6],"algorithm":[7],"to":[8,13],"select":[9],"useful":[10],"training":[11,47],"samples":[12],"minimize":[14],"annotation":[15],"cost.":[16],"This":[17],"is":[18,186],"now":[19],"an":[20,62,86],"essential":[21],"tool":[22],"for":[23],"building":[24],"low-resource":[25],"syntactic":[26],"analyzers":[27],"such":[28],"as":[29,114],"part-of-speech":[30],"(POS)":[31],"taggers.":[32],"Existing":[33],"AL":[34,113,138,142],"heuristics":[35,99],"are":[36,100],"generally":[37],"designed":[38],"on":[39,105,130],"the":[40,80,92,110,120,131,154,180],"principle":[41],"of":[42,58,95,112,125,156,159],"selecting":[43,115],"uncertain":[44],"yet":[45],"representative":[46],"instances,":[48],"where":[49,89],"annotating":[50],"these":[51,97],"instances":[52,116],"may":[53],"reduce":[54,119],"large":[56],"number":[57],"errors.":[59],"However,":[60],"in":[61,85],"empirical":[63],"study":[64],"across":[65],"six":[66],"typologically":[67],"diverse":[68],"languages":[69,133],"(German,":[70],"Swedish,":[71],"Galician,":[72],"North":[73],"Sami,":[74],"Persian,":[75],"and":[76,167],"Ukrainian),":[77],"we":[78,90,108,162],"found":[79],"surprising":[81],"result":[82],"that":[83,117,135,176],"even":[84],"oracle":[87,181],"scenario":[88],"know":[91],"true":[93],"uncertainty":[94],"predictions,":[96],"current":[98],"far":[101],"from":[102],"optimal.":[103],"Based":[104],"this":[106],"analysis,":[107],"pose":[109],"problem":[111],"maximally":[118],"confusion":[121],"between":[122],"particular":[123],"pairs":[124],"output":[126],"tags.":[127],"Extensive":[128],"experimentation":[129],"aforementioned":[132],"shows":[134],"our":[136,171],"proposed":[137,172],"strategy":[139,173],"outperforms":[140],"other":[141],"strategies":[143],"by":[144],"significant":[146],"margin.":[147],"We":[148],"also":[149],"present":[150],"auxiliary":[151],"results":[152],"demonstrating":[153,169],"importance":[155],"proper":[157],"calibration":[158],"models,":[160],"which":[161],"ensure":[163],"through":[164],"cross-view":[165],"training,":[166],"analysis":[168],"how":[170],"selects":[174],"examples":[175],"more":[177],"closely":[178],"follow":[179],"distribution.":[183],"The":[184],"code":[185],"publicly":[187],"released":[188],"here.":[189],"1":[190]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}