{"id":"https://openalex.org/W2889487253","doi":"https://doi.org/10.18653/v1/d18-1061","title":"Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging","display_name":"Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889487253","doi":"https://doi.org/10.18653/v1/d18-1061","mag":"2889487253"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1061","pdf_url":"https://www.aclweb.org/anthology/D18-1061.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1061.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"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","NL"],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":["Department of Computer Science IT University of Copenhagen Rued Langgaards Vej 7, 2300 Copenhagen S, Denmark","University of Groningen, Groningen, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science IT University of Copenhagen Rued Langgaards Vej 7, 2300 Copenhagen S, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090835657","display_name":"\u017beljko Agi\u0107","orcid":null},"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":"\u017deljko Agi\u0107","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3379,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68844836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"614","last_page":"620"},"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8191617131233215},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.8014588356018066},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7982404232025146},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6309678554534912},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6204756498336792},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5436986088752747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5154441595077515},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.49823927879333496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49380144476890564},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41242778301239014},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.3290693163871765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07125014066696167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191617131233215},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.8014588356018066},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7982404232025146},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6309678554534912},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6204756498336792},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5436986088752747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5154441595077515},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.49823927879333496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49380144476890564},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41242778301239014},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.3290693163871765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07125014066696167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/d18-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1061","pdf_url":"https://www.aclweb.org/anthology/D18-1061.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/14bcfb02-efc4-4508-9e7c-0b8e592a88db","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/14bcfb02-efc4-4508-9e7c-0b8e592a88db","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":"Plank, B & Agic, Z 2018, Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging. in Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1808.09733","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.09733","pdf_url":"https://arxiv.org/pdf/1808.09733","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"},{"id":"mag:2889487253","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.09733.pdf","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":"doi:10.48550/arxiv.1808.09733","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.09733","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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1061","pdf_url":"https://www.aclweb.org/anthology/D18-1061.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889487253.pdf","grobid_xml":"https://content.openalex.org/works/W2889487253.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1523296404","https://openalex.org/W1574126082","https://openalex.org/W2016630033","https://openalex.org/W2064675550","https://openalex.org/W2142523187","https://openalex.org/W2143995218","https://openalex.org/W2161044106","https://openalex.org/W2162302090","https://openalex.org/W2168199177","https://openalex.org/W2251227481","https://openalex.org/W2410082850","https://openalex.org/W2574182335","https://openalex.org/W2610661645","https://openalex.org/W2626433756","https://openalex.org/W2738591886","https://openalex.org/W2759412944","https://openalex.org/W2950121111","https://openalex.org/W2950886545","https://openalex.org/W2952566282","https://openalex.org/W2955750298","https://openalex.org/W2963641259","https://openalex.org/W2963907318","https://openalex.org/W2964090065"],"related_works":["https://openalex.org/W2773052985","https://openalex.org/W2886711982","https://openalex.org/W2947015347","https://openalex.org/W2140497009","https://openalex.org/W2899047179","https://openalex.org/W2952289666","https://openalex.org/W2895414369","https://openalex.org/W2467585580","https://openalex.org/W1636572971","https://openalex.org/W3197618824","https://openalex.org/W2537144109","https://openalex.org/W2902354595","https://openalex.org/W3109527089","https://openalex.org/W3172196531","https://openalex.org/W2889191148","https://openalex.org/W2250320249","https://openalex.org/W2963863756","https://openalex.org/W2789718859","https://openalex.org/W3100843744","https://openalex.org/W2923290299"],"abstract_inverted_index":{"We":[0],"introduce":[1],"DSDS:":[2],"a":[3,40,52],"cross-lingual":[4],"neural":[5],"part-of-speech":[6],"tagger":[7],"that":[8],"learns":[9],"from":[10],"disparate":[11],"sources":[12],"of":[13,21,55],"distant":[14],"supervision,":[15],"and":[16,35],"realistically":[17],"scales":[18],"to":[19,60],"hundreds":[20],"low-resource":[22],"languages.":[23],"The":[24,43],"model":[25],"exploits":[26],"annotation":[27],"projection,":[28],"instance":[29],"selection,":[30],"tag":[31],"dictionaries,":[32],"morphological":[33],"lexicons,":[34],"distributed":[36],"representations,":[37],"all":[38],"in":[39,51],"uniform":[41],"framework.":[42],"approach":[44],"is":[45],"simple,":[46],"yet":[47],"surprisingly":[48],"effective,":[49],"resulting":[50],"new":[53],"state":[54],"the":[56],"art":[57],"without":[58],"access":[59],"any":[61],"gold":[62],"annotated":[63],"data.":[64]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}