{"id":"https://openalex.org/W2021254338","doi":"https://doi.org/10.1145/1871840.1871841","title":"The nature of noise in linguistic corpora","display_name":"The nature of noise in linguistic corpora","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2021254338","doi":"https://doi.org/10.1145/1871840.1871841","mag":"2021254338"},"language":"en","primary_location":{"id":"doi:10.1145/1871840.1871841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091866119","display_name":"Randy Goebel","orcid":"https://orcid.org/0000-0002-0739-2946"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Randy Goebel","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037189732","display_name":"Shane Bergsma","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shane Bergsma","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652476","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-5503-2929"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110248832","display_name":"Christoph Ringlstetter","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Ringlstetter","raw_affiliation_strings":["Ludwig Maximilians Universit\u00e4t, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Maximilians Universit\u00e4t, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100743275","display_name":"Mi-Young Kim","orcid":"https://orcid.org/0000-0002-2598-6932"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mi-Young Kim","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.13499541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T12881","display_name":"linguistics and terminology studies","score":0.9614999890327454,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.9550999999046326,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.8661572933197021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820876836776733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6063147783279419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5227280259132385},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.44215330481529236}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.8661572933197021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820876836776733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6063147783279419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227280259132385},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44215330481529236},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871840.1871841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W2390279801","https://openalex.org/W3125814499","https://openalex.org/W3204019825"],"abstract_inverted_index":{"'For":[0],"the":[1,24,36,49],"past":[2],"4-5":[3],"years,":[4],"we've":[5],"been":[6],"investigating":[7],"a":[8,43,54],"variety":[9,55],"of":[10,26,45,56],"computational":[11],"methods":[12],"for":[13],"extracting":[14],"linguistic":[15],"structures":[16],"from":[17,35,66],"relatively":[18],"large":[19],"language":[20,30],"corpora.":[21],"These":[22],"include":[23],"use":[25],"well-known":[27],"standard":[28],"labeled":[29],"resources":[31,64],"such":[32],"as":[33,40,42],"those":[34],"Linguistic":[37],"Data":[38],"Consortium,":[39],"well":[41],"spectrum":[44],"unlabeled":[46],"resources,":[47],"including":[48],"Google":[50],"n-gram":[51],"repository":[52],"and":[53,62],"more":[57],"specific":[58],"search":[59],"engine":[60],"query":[61],"answer":[63],"(e.g.,":[65],"Sogou).":[67]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
