{"id":"https://openalex.org/W2955750298","doi":"https://doi.org/10.18653/v1/w18-3401","title":"Character-level Supervision for Low-resource POS Tagging","display_name":"Character-level Supervision for Low-resource POS Tagging","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2955750298","doi":"https://doi.org/10.18653/v1/w18-3401","mag":"2955750298"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-3401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3401","pdf_url":"https://www.aclweb.org/anthology/W18-3401.pdf","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 Workshop on Deep Learning Approaches for Low-Resource NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-3401.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082874907","display_name":"Katharina Kann","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katharina Kann","raw_affiliation_strings":["Center for Data Science, New York University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013472329","display_name":"Johannes Bjerva","orcid":"https://orcid.org/0000-0002-9512-0739"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Johannes Bjerva","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018976680","display_name":"Isabelle Augenstein","orcid":"https://orcid.org/0000-0003-1562-7909"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Isabelle Augenstein","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":["Department of Computer Science, IT University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, IT University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082874907"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":3.2153,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93717393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9945999979972839,"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":0.6835498809814453},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6263927221298218},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4569661021232605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3262823224067688},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08249148726463318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0646195113658905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6835498809814453},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6263927221298218},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4569661021232605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3262823224067688},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08249148726463318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0646195113658905},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w18-3401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3401","pdf_url":"https://www.aclweb.org/anthology/W18-3401.pdf","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 Workshop on Deep Learning Approaches for Low-Resource NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/e7843e81-689d-430c-89b0-39032a17606e","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/e7843e81-689d-430c-89b0-39032a17606e","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kann, K, Bjerva, J, Augenstein, I, Plank, B & S\u00f8gaard, A 2018, Character-level Supervision for Low-resource POS Tagging. in Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP . Association for Computational Linguistics, Melbourne, pp. 1-11.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/551721f9-a037-4133-92bc-d3d533884c4f","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/551721f9-a037-4133-92bc-d3d533884c4f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kann , K , Bjerva , J , Augenstein , I , Plank , B & S\u00f8gaard , A 2018 , Character-level Supervision for Low-resource POS Tagging . in Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP . Association for Computational Linguistics , pp. 1\u201311 , Workshop on Deep Learning Approaches for Low-Resource NLP , Melbourne , Australia , 19/07/2018 .","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-3401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3401","pdf_url":"https://www.aclweb.org/anthology/W18-3401.pdf","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 Workshop on Deep Learning Approaches for Low-Resource NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338388","display_name":"Eurostars","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2955750298.pdf","grobid_xml":"https://content.openalex.org/works/W2955750298.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W175533286","https://openalex.org/W1522263329","https://openalex.org/W1522301498","https://openalex.org/W1574126082","https://openalex.org/W1860935423","https://openalex.org/W1899794420","https://openalex.org/W2016630033","https://openalex.org/W2025198378","https://openalex.org/W2098830640","https://openalex.org/W2099873701","https://openalex.org/W2102294561","https://openalex.org/W2115774663","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2147880316","https://openalex.org/W2161044106","https://openalex.org/W2164076936","https://openalex.org/W2164119735","https://openalex.org/W2170973209","https://openalex.org/W2231920551","https://openalex.org/W2250471514","https://openalex.org/W2251227481","https://openalex.org/W2251743902","https://openalex.org/W2301095666","https://openalex.org/W2308486447","https://openalex.org/W2351252181","https://openalex.org/W2515098781","https://openalex.org/W2516255829","https://openalex.org/W2525907473","https://openalex.org/W2550821151","https://openalex.org/W2555745756","https://openalex.org/W2569308312","https://openalex.org/W2592170186","https://openalex.org/W2617039999","https://openalex.org/W2623845346","https://openalex.org/W2624275270","https://openalex.org/W2767862400","https://openalex.org/W2949369097","https://openalex.org/W2951784689","https://openalex.org/W2952729433","https://openalex.org/W2962680795","https://openalex.org/W2962705709","https://openalex.org/W2963208801","https://openalex.org/W2963635689","https://openalex.org/W2963706742","https://openalex.org/W2963752701","https://openalex.org/W2964034111","https://openalex.org/W2964084097","https://openalex.org/W2964090065","https://openalex.org/W2964094426","https://openalex.org/W2964121744","https://openalex.org/W2964170290","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W4295803838","https://openalex.org/W4300062960"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713"],"abstract_inverted_index":{"Neural":[0],"part-of-speech":[1],"(POS)":[2],"taggers":[3,31],"are":[4],"known":[5],"to":[6,64,75,138],"not":[7],"perform":[8],"well":[9],"with":[10,79,93,154],"little":[11],"training":[12,34],"data.":[13],"As":[14],"a":[15,35,40,108,139],"step":[16],"towards":[17],"overcoming":[18],"this":[19],"problem,":[20],"we":[21,52],"present":[22],"an":[23,47],"architecture":[24,106],"for":[25,123,144],"learning":[26],"more":[27],"robust":[28],"neural":[29,132],"POS":[30,125,133,141],"by":[32,147,162],"jointly":[33],"hierarchical,":[36],"recurrent":[37,41],"model":[38],"and":[39,67,87,160],"characterbased":[42],"sequence-to-sequence":[43],"network":[44],"supervised":[45],"using":[46,128],"auxiliary":[48,81],"objective.":[49],"This":[50],"way,":[51],"introduce":[53],"stronger":[54],"character-level":[55],"supervision":[56],"into":[57],"the":[58,136],"model,":[59],"which":[60],"enables":[61],"better":[62],"generalization":[63],"unseen":[65],"words":[66],"provides":[68],"regularization,":[69],"making":[70],"our":[71,104],"encoding":[72],"less":[73],"prone":[74],"overfitting.":[76],"We":[77],"experiment":[78],"three":[80],"tasks:":[82],"lemmatization,":[83],"character-based":[84,88],"word":[85],"autoencoding,":[86],"random":[89],"string":[90],"autoencoding.":[91],"Experiments":[92],"minimal":[94],"amounts":[95],"of":[96],"labeled":[97],"data":[98],"on":[99,114,152],"34":[100],"languages":[101,153],"show":[102],"that":[103],"new":[105],"outperforms":[107],"single-task":[109],"baseline":[110],"and,":[111],"surprisingly,":[112],"that,":[113],"average,":[115],"raw":[116],"text":[117],"autoencoding":[118],"can":[119],"be":[120],"as":[121,127],"beneficial":[122],"lowresource":[124],"tagging":[126],"lemma":[129],"information.":[130],"Our":[131],"tagger":[134,142],"closes":[135],"gap":[137],"state-of-the-art":[140],"(MarMoT)":[143],"low-resource":[145],"scenarios":[146],"43%,":[148],"even":[149],"outperforming":[150],"it":[151],"templatic":[155],"morphology,":[156],"e.g.,":[157],"Arabic,":[158],"Hebrew,":[159],"Turkish,":[161],"some":[163],"margin.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}