{"id":"https://openalex.org/W3083311033","doi":"https://doi.org/10.48550/arxiv.2009.02043","title":"Data Readiness for Natural Language Processing","display_name":"Data Readiness for Natural Language Processing","publication_year":2020,"publication_date":"2020-09-04","ids":{"openalex":"https://openalex.org/W3083311033","doi":"https://doi.org/10.48550/arxiv.2009.02043","mag":"3083311033"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2009.02043","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02043","pdf_url":"https://arxiv.org/pdf/2009.02043","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.02043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Olsson, Fredrik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olsson, Fredrik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058048696","display_name":"Magnus Sahlgren","orcid":"https://orcid.org/0000-0001-5100-0535","observed_orcids":["https://orcid.org/0000-0001-5100-0535"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahlgren, Magnus","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":false,"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/T11719","display_name":"Data Quality and Management","score":0.3149000108242035,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.3149000108242035,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.25290000438690186,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.1695999950170517,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-readiness","display_name":"data readiness","score":0.9990000128746033},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.8460000157356262},{"id":"https://openalex.org/keywords/data-preparation","display_name":"data preparation","score":0.7950000166893005},{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.9610000252723694},{"id":"https://openalex.org/keywords/data-availability","display_name":"data availability","score":0.8080000281333923},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.5569999814033508},{"id":"https://openalex.org/keywords/machine-learning-data","display_name":"machine learning data","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876756548881531},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6034384965896606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5460169911384583},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5435556769371033},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5337371230125427},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4808679223060608},{"id":"https://openalex.org/C121426985","wikidata":"https://www.wikidata.org/wiki/Q591763","display_name":"Private sector","level":2,"score":0.4442179203033447},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.43386995792388916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33132657408714294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14650040864944458},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09973594546318054},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2009.02043","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02043","pdf_url":"https://arxiv.org/pdf/2009.02043","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,"listed_in":[],"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.2009.02043","doi":"https://doi.org/10.48550/arxiv.2009.02043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.02043","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,"listed_in":[],"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:2009.02043","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02043","pdf_url":"https://arxiv.org/pdf/2009.02043","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2612743528","https://openalex.org/W2911625428","https://openalex.org/W2912968987","https://openalex.org/W3023201182","https://openalex.org/W3097849828"],"related_works":["https://openalex.org/W4283262748","https://openalex.org/W2502773048","https://openalex.org/W4252362398","https://openalex.org/W48866389","https://openalex.org/W2117651364","https://openalex.org/W3112533414","https://openalex.org/W2490481324","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"This":[0],"document":[1,39],"concerns":[2],"data":[3,29,75],"readiness":[4],"in":[5,53,67,76],"the":[6,38,43,68],"context":[7],"of":[8,37],"machine":[9],"learning":[10],"and":[11,27,46,64,70],"Natural":[12],"Language":[13],"Processing.":[14],"It":[15],"describes":[16],"how":[17],"an":[18,57],"organization":[19],"may":[20],"proceed":[21],"to":[22,30,73],"identify,":[23],"make":[24],"available,":[25],"validate,":[26],"prepare":[28],"facilitate":[31],"automated":[32],"analysis":[33],"methods.":[34],"The":[35],"contents":[36],"is":[40],"based":[41],"on":[42],"practical":[44],"challenges":[45],"frequently":[47],"asked":[48],"questions":[49],"we":[50],"have":[51],"encountered":[52],"our":[54],"work":[55],"as":[56],"applied":[58],"research":[59],"institute":[60],"with":[61],"helping":[62],"organizations":[63],"companies,":[65],"both":[66],"public":[69],"private":[71],"sectors,":[72],"use":[74],"their":[77],"business":[78],"processes.":[79]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}