{"id":"https://openalex.org/W2735393842","doi":"https://doi.org/10.18653/v1/w17-4404","title":"To normalize, or not to normalize: The impact of normalization on Part-of-Speech tagging","display_name":"To normalize, or not to normalize: The impact of normalization on Part-of-Speech tagging","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2735393842","doi":"https://doi.org/10.18653/v1/w17-4404","mag":"2735393842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4404","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4404","pdf_url":"https://www.aclweb.org/anthology/W17-4404.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4404.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156"},"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"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Rob van der Goot","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"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/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040564747","display_name":"Malvina Nissim","orcid":"https://orcid.org/0000-0001-5289-0971"},"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"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Malvina Nissim","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039811894"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":3.1077,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93323089,"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":"31","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T12031","display_name":"Speech and dialogue systems","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/normalization","display_name":"Normalization (sociology)","score":0.9221308827400208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7417439818382263},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.7355175614356995},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6756722331047058},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5584885478019714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537848174571991},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5248691439628601},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49221816658973694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47039780020713806},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4667057991027832},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.44657012820243835},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.35145583748817444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3351939916610718}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9221308827400208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7417439818382263},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.7355175614356995},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6756722331047058},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5584885478019714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537848174571991},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5248691439628601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49221816658973694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47039780020713806},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4667057991027832},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.44657012820243835},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.35145583748817444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3351939916610718},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-4404","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4404","pdf_url":"https://www.aclweb.org/anthology/W17-4404.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4404","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4404","pdf_url":"https://www.aclweb.org/anthology/W17-4404.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319634","display_name":"Nuance Foundation","ror":null},{"id":"https://openalex.org/F4320320933","display_name":"Rijksuniversiteit Groningen","ror":"https://ror.org/012p63287"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2735393842.pdf","grobid_xml":"https://content.openalex.org/works/W2735393842.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W122290181","https://openalex.org/W371426616","https://openalex.org/W1597032530","https://openalex.org/W1614298861","https://openalex.org/W1991133427","https://openalex.org/W2101461018","https://openalex.org/W2101761627","https://openalex.org/W2105103433","https://openalex.org/W2146867136","https://openalex.org/W2153848201","https://openalex.org/W2250368612","https://openalex.org/W2250423567","https://openalex.org/W2250729567","https://openalex.org/W2251406234","https://openalex.org/W2296194829","https://openalex.org/W2296474619","https://openalex.org/W2516572534","https://openalex.org/W2548489473","https://openalex.org/W2571911508","https://openalex.org/W2572352420","https://openalex.org/W2740787599","https://openalex.org/W2760845412","https://openalex.org/W2911964244","https://openalex.org/W2950577311","https://openalex.org/W2963196639","https://openalex.org/W2963386475","https://openalex.org/W2963837895","https://openalex.org/W2964090065","https://openalex.org/W4233787372","https://openalex.org/W4297803344"],"related_works":["https://openalex.org/W1965453504","https://openalex.org/W2396342956","https://openalex.org/W2169508526","https://openalex.org/W2486838646","https://openalex.org/W2626026432","https://openalex.org/W2251183413","https://openalex.org/W2949108231","https://openalex.org/W3128305375","https://openalex.org/W2006539681","https://openalex.org/W2046224275"],"abstract_inverted_index":{"Does":[0],"normalization":[1,25,43,52,71],"help":[2],"Part-of-Speech":[3],"(POS)":[4],"tagging":[5,46,89],"accuracy":[6],"on":[7,20,44],"noisy,":[8],"noncanonical":[9],"data?":[10],"To":[11],"the":[12,21,39],"best":[13],"of":[14,24,41,47,59],"our":[15],"knowledge,":[16],"little":[17],"is":[18,34,92],"known":[19],"actual":[22],"impact":[23],"in":[26,63],"a":[27,88,95],"real-world":[28],"scenario,":[29],"where":[30],"gold":[31],"error":[32],"detection":[33],"not":[35,75],"available.":[36],"We":[37,49],"investigate":[38],"effect":[40],"automatic":[42],"POS":[45],"tweets.":[48],"also":[50],"compare":[51],"to":[53],"strategies":[54],"that":[55,70,91],"leverage":[56],"large":[57],"amounts":[58],"unlabeled":[60],"data":[61],"kept":[62],"its":[64],"raw":[65],"form.":[66],"Our":[67],"results":[68],"show":[69],"helps,":[72],"but":[73],"does":[74],"add":[76],"consistently":[77],"beyond":[78],"just":[79],"word":[80],"embedding":[81],"layer":[82],"initialization.":[83],"The":[84],"latter":[85],"approach":[86],"yields":[87],"model":[90],"competitive":[93],"with":[94],"Twitter":[96],"state-of-the-art":[97],"tagger.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}