{"id":"https://openalex.org/W2509163649","doi":"https://doi.org/10.18653/v1/w16-2608","title":"UdS-(retrain|distributional|surface): Improving POS Tagging for OOV Words in German CMC and Web Data","display_name":"UdS-(retrain|distributional|surface): Improving POS Tagging for OOV Words in German CMC and Web Data","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2509163649","doi":"https://doi.org/10.18653/v1/w16-2608","mag":"2509163649"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2608","pdf_url":"https://www.aclweb.org/anthology/W16-2608.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 10th Web as Corpus Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2608.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022361649","display_name":"Jakob Prange","orcid":"https://orcid.org/0000-0002-4640-5295"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jakob Prange","raw_affiliation_strings":["Department of Computational Linguistics Saarland University Saarbrcken Germany","Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbrcken Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072701486","display_name":"Andrea Horbach","orcid":"https://orcid.org/0009-0004-3680-3304"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrea Horbach","raw_affiliation_strings":["Department of Computational Linguistics Saarland University Saarbrcken Germany","Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbrcken Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111900696","display_name":"Stefan Thater","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Thater","raw_affiliation_strings":["Department of Computational Linguistics Saarland University Saarbrcken Germany","Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbrcken Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Department of Computational Linguistics Saarland University Saarbr\u00fccken Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022361649"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86897227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"71"},"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":0.9995999932289124,"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":0.991599977016449,"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":0.7641987204551697},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7151551842689514},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7083319425582886},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5719879269599915},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5359417200088501},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.518068790435791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5084677934646606},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49693062901496887},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46282893419265747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4590988755226135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3337799310684204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12156316637992859},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0688883364200592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641987204551697},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7151551842689514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7083319425582886},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5719879269599915},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5359417200088501},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.518068790435791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084677934646606},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49693062901496887},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46282893419265747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4590988755226135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3337799310684204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12156316637992859},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0688883364200592},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w16-2608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2608","pdf_url":"https://www.aclweb.org/anthology/W16-2608.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 10th Web as Corpus Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:117836","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/117836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceobject"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2608","pdf_url":"https://www.aclweb.org/anthology/W16-2608.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 10th Web as Corpus Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2509163649.pdf","grobid_xml":"https://content.openalex.org/works/W2509163649.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W157541337","https://openalex.org/W1631260214","https://openalex.org/W1986330201","https://openalex.org/W2004739122","https://openalex.org/W2052847729","https://openalex.org/W2075040270","https://openalex.org/W2250553731","https://openalex.org/W2335306878","https://openalex.org/W2402670915","https://openalex.org/W3095590940","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2315527029","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"We":[0,64],"present":[1],"in":[2],"this":[3],"paper":[4],"our":[5],"three":[6],"system":[7,21,48],"submissions":[8],"for":[9],"the":[10,15,46,66,70],"POS":[11],"tagging":[12],"subtask":[13],"of":[14,39,45,57],"Empirist":[16],"Shared":[17],"Task:":[18],"Our":[19],"baseline":[20,47],"UdS-retrain":[22],"extends":[23],"a":[24,55],"standard":[25],"training":[26,30],"dataset":[27],"with":[28],"in-domain":[29],"data;":[31],"UdSdistributional":[32],"and":[33,60],"UdS-surface":[34],"add":[35],"two":[36],"different":[37],"ways":[38],"handling":[40],"OOV":[41],"words":[42],"on":[43],"top":[44],"by":[49],"using":[50,69],"either":[51],"distributional":[52,71],"information":[53],"or":[54],"combination":[56],"surface":[58],"similarity":[59],"language":[61],"model":[62],"information.":[63],"reach":[65],"best":[67],"performance":[68],"model.":[72]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
