{"id":"https://openalex.org/W4400141897","doi":"https://doi.org/10.48550/arxiv.2406.19172","title":"Annotation Errors and NER: A Study with OntoNotes 5.0","display_name":"Annotation Errors and NER: A Study with OntoNotes 5.0","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400141897","doi":"https://doi.org/10.48550/arxiv.2406.19172"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.19172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19172","pdf_url":"https://arxiv.org/pdf/2406.19172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.19172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039723280","display_name":"Gabriel Bernier-Colborne","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernier-Colborne, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030558411","display_name":"Sowmya Vajjala","orcid":"https://orcid.org/0000-0002-4033-9936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vajjala, Sowmya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7398999929428101,"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":0.7398999929428101,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.6883000135421753,"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":0.7726961970329285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36577165126800537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33985650539398193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24671673774719238}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7726961970329285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36577165126800537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33985650539398193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24671673774719238}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.19172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19172","pdf_url":"https://arxiv.org/pdf/2406.19172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2406.19172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.19172","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.19172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19172","pdf_url":"https://arxiv.org/pdf/2406.19172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400141897.pdf","grobid_xml":"https://content.openalex.org/works/W4400141897.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","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/W2625833328","https://openalex.org/W1533177136"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recognition":[2],"(NER)":[3],"is":[4,12,47,150],"a":[5,85],"well-studied":[6],"problem":[7],"in":[8,38,62,80,126],"NLP.":[9],"However,":[10],"there":[11,149],"much":[13],"less":[14],"focus":[15],"on":[16],"studying":[17],"NER":[18,24,51,102,167],"datasets,":[19,118,168],"compared":[20],"to":[21,34,104],"developing":[22],"new":[23],"models.":[25],"In":[26,65],"this":[27],"paper,":[28],"we":[29,70],"employed":[30,164],"three":[31,101],"simple":[32],"techniques":[33,56],"detect":[35],"annotation":[36,141,153],"errors":[37],"the":[39,48,60,72,81,95,109,113,116,136],"OntoNotes":[40],"5.0":[41],"corpus":[42,52],"for":[43,53,133],"English":[44],"NER,":[45],"which":[46,119],"largest":[49],"available":[50],"English.":[54],"Our":[55],"corrected":[57,71],"~10%":[58],"of":[59,67,76,78,92,97,124,135],"sentences":[61],"train/dev/test":[63],"data.":[64],"terms":[66],"entity":[68,137],"mentions,":[69],"span":[73],"and/or":[74],"type":[75],"~8%":[77],"mentions":[79],"dataset,":[82],"while":[83],"adding/deleting/splitting/merging":[84],"few":[86],"more.":[87],"These":[88],"are":[89,145,157],"large":[90,130],"numbers":[91],"changes,":[93],"considering":[94],"size":[96],"OntoNotes.":[98],"We":[99],"used":[100],"libraries":[103],"train,":[105],"evaluate":[106],"and":[107,115,148,161,169],"compare":[108],"models":[110],"trained":[111],"with":[112,129,165],"original":[114],"re-annotated":[117],"showed":[120],"an":[121],"average":[122],"improvement":[123],"1.23%":[125],"overall":[127],"F-scores,":[128],"(>10%)":[131],"improvements":[132],"some":[134,151],"types.":[138],"While":[139],"our":[140],"error":[142],"detection":[143],"methods":[144],"not":[146],"exhaustive":[147],"manual":[152],"effort":[154],"involved,":[155],"they":[156],"largely":[158],"language":[159],"agnostic":[160],"can":[162],"be":[163],"other":[166,170],"sequence":[171],"labelling":[172],"tasks.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}