{"id":"https://openalex.org/W2252111006","doi":"https://doi.org/10.3115/v1/w15-1617","title":"Non-canonical language is not harder to annotate than canonical language","display_name":"Non-canonical language is not harder to annotate than canonical language","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252111006","doi":"https://doi.org/10.3115/v1/w15-1617","mag":"2252111006"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w15-1617","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w15-1617","pdf_url":"https://doi.org/10.3115/v1/w15-1617","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The 9th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w15-1617","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Barbara Plank","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014924576","display_name":"H\u0117ctor Mart\u00ednez Alonso","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Mart\u00ednez Alonso","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088832285"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8897,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83687553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9961000084877014,"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/annotation","display_name":"Annotation","score":0.8620589971542358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858333587646484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6108137369155884},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6042249202728271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509896278381348},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4556792378425598},{"id":"https://openalex.org/keywords/non-canonical","display_name":"Non canonical","score":0.4105871021747589},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34190475940704346},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33068519830703735},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19158291816711426}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8620589971542358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858333587646484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6108137369155884},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6042249202728271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509896278381348},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4556792378425598},{"id":"https://openalex.org/C3018844941","wikidata":"https://www.wikidata.org/wiki/Q6718887","display_name":"Non canonical","level":2,"score":0.4105871021747589},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34190475940704346},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33068519830703735},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19158291816711426},{"id":"https://openalex.org/C95444343","wikidata":"https://www.wikidata.org/wiki/Q7141","display_name":"Cell biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w15-1617","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w15-1617","pdf_url":"https://doi.org/10.3115/v1/w15-1617","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The 9th Linguistic Annotation Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/bdee84d3-c442-4e72-8056-5fad192e2ae9","is_oa":true,"landing_page_url":"http://www.aclweb.org/anthology/W15-1617","pdf_url":"https://aclanthology.org/W15-1617.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Plank , B , Martinez Alonso , H & S\u00f8gaard , A 2015 , Non-canonical language is not harder to annotate than canonical language . in The 9th Linguistic Annotation Workshop (held in conjuncion with NAACL 2015) : LAW IX . Association for Computational Linguistics , pp. 148-151 . < http://www.aclweb.org/anthology/W15-1617 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/bdee84d3-c442-4e72-8056-5fad192e2ae9","is_oa":true,"landing_page_url":"https://curis.ku.dk/portal/da/publications/noncanonical-language-is-not-harder-to-annotate-than-canonical-language(bdee84d3-c442-4e72-8056-5fad192e2ae9).html","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/v1/w15-1617","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w15-1617","pdf_url":"https://doi.org/10.3115/v1/w15-1617","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The 9th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252111006.pdf","grobid_xml":"https://content.openalex.org/works/W2252111006.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W191693080","https://openalex.org/W655994999","https://openalex.org/W1970849810","https://openalex.org/W2105103433","https://openalex.org/W2116410915"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W4243973949","https://openalex.org/W2625833328","https://openalex.org/W4405124681"],"abstract_inverted_index":{"As":[0],"researchers":[1],"developing":[2],"robust":[3],"NLP":[4],"for":[5,100],"a":[6,40],"wide":[7],"range":[8],"of":[9,21,33,75],"text":[10],"types,":[11],"we":[12,38,81],"are":[13],"often":[14],"confronted":[15],"with":[16,48,92],"the":[17],"prejudice":[18],"that":[19,25,70,84,96],"annotation":[20,32,42,74],"non-canonical":[22,76],"language":[23,77],"(whatever":[24],"means)":[26],"is":[27,78],"somehow":[28],"more":[29],"arbitrary":[30],"than":[31],"canonical":[34],"language.To":[35],"investigate":[36],"this,":[37],"present":[39],"small":[41],"study":[43,68],"where":[44],"annotators":[45,98],"were":[46],"asked,":[47],"minimal":[49],"guidelines,":[50],"to":[51,66],"identify":[52],"main":[53],"predicates":[54],"and":[55],"arguments":[56],"in":[57,86],"sentences":[58],"across":[59],"five":[60],"different":[61,101],"domains,":[62],"ranging":[63],"from":[64],"newswire":[65],"Twitter.Our":[67],"indicates":[69],"(at":[71],"least":[72],"such)":[73],"not":[79],"harder.However,":[80],"also":[82],"observe":[83],"agreements":[85],"social":[87,105],"media":[88,106],"domains":[89],"correlate":[90],"less":[91],"model":[93],"confidence,":[94],"suggesting":[95],"maybe":[97],"disagree":[99],"reasons":[102],"when":[103],"annotating":[104],"data.":[107]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
