{"id":"https://openalex.org/W2251687211","doi":"https://doi.org/10.3115/v1/w14-4907","title":"Optimizing annotation efforts to build reliable annotated corpora for training statistical models","display_name":"Optimizing annotation efforts to build reliable annotated corpora for training statistical models","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251687211","doi":"https://doi.org/10.3115/v1/w14-4907","mag":"2251687211"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-4907","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4907","pdf_url":"https://doi.org/10.3115/v1/w14-4907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th 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/w14-4907","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047002517","display_name":"Cyril Grouin","orcid":"https://orcid.org/0000-0001-5809-188X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cyril Grouin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774746","display_name":"Thomas Lavergne","orcid":"https://orcid.org/0000-0002-9498-4551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Lavergne","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005499870","display_name":"Aur\u00e9lie N\u00e9v\u00e9ol","orcid":"https://orcid.org/0000-0002-1846-9144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aurelie Neveol","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047002517"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1143,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90151974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8305702209472656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185774087905884},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6004528999328613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5197789072990417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4604421854019165},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4412565529346466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39323142170906067},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.360990047454834}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8305702209472656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185774087905884},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6004528999328613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5197789072990417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4604421854019165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4412565529346466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39323142170906067},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.360990047454834},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-4907","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4907","pdf_url":"https://doi.org/10.3115/v1/w14-4907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.8215","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.8215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-4907.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-4907","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4907","pdf_url":"https://doi.org/10.3115/v1/w14-4907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251687211.pdf","grobid_xml":"https://content.openalex.org/works/W2251687211.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W136468075","https://openalex.org/W149153798","https://openalex.org/W1480287196","https://openalex.org/W1574901103","https://openalex.org/W1632114991","https://openalex.org/W2045718189","https://openalex.org/W2050611670","https://openalex.org/W2102162869","https://openalex.org/W2102575587","https://openalex.org/W2115570566","https://openalex.org/W2116705992","https://openalex.org/W2121227244","https://openalex.org/W2137263933","https://openalex.org/W2141766660","https://openalex.org/W2158049734","https://openalex.org/W2160986985","https://openalex.org/W2251519152"],"related_works":["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","https://openalex.org/W4380994516","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Creating":[0],"high-quality":[1],"manual":[2],"annotations":[3],"on":[4,73],"text":[5],"corpus":[6,52],"is":[7],"time-consuming":[8],"and":[9,41,70],"often":[10],"requires":[11],"the":[12,32,77],"work":[13],"of":[14,31,48,53,67,79],"experts.":[15],"In":[16],"order":[17],"to":[18,75],"explore":[19],"methods":[20],"for":[21,57],"optimizing":[22],"annotation":[23,33,81],"efforts,":[24],"we":[25,64],"study":[26],"three":[27],"key":[28],"time":[29],"burdens":[30],"process:":[34],"(i)":[35],"multiple":[36],"annotations,":[37,40],"(ii)":[38],"consensus":[39],"(iii)":[42],"careful":[43],"annotations.":[44],"Through":[45],"a":[46,51],"series":[47],"experiments":[49],"using":[50],"clinical":[54],"documents":[55],"annotated":[56],"personally":[58],"identifiable":[59],"information":[60],"written":[61],"in":[62],"French,":[63],"address":[65],"each":[66],"these":[68],"aspects":[69],"draw":[71],"conclusions":[72],"how":[74],"make":[76],"most":[78],"an":[80],"effort.":[82],"1":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}