{"id":"https://openalex.org/W2740834240","doi":"https://doi.org/10.18653/v1/w17-1603","title":"A Quantitative Study of Data in the NLP community","display_name":"A Quantitative Study of Data in the NLP community","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740834240","doi":"https://doi.org/10.18653/v1/w17-1603","mag":"2740834240"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1603","pdf_url":"https://www.aclweb.org/anthology/W17-1603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACL Workshop on Ethics in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1603.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012193392","display_name":"Margot Mieskes","orcid":"https://orcid.org/0009-0006-2268-4804"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Margot Mieskes","raw_affiliation_strings":["Information Science Darmstadt University of Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Science Darmstadt University of Applied Sciences","institution_ids":["https://openalex.org/I107257983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012193392"],"corresponding_institution_ids":["https://openalex.org/I107257983"],"apc_list":null,"apc_paid":null,"fwci":2.2148,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91605498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9983000159263611,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8151113986968994},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6556409597396851},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.6138624548912048},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5634898543357849},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4673754572868347},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46391549706459045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44163233041763306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013128876686096},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3435731530189514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151113986968994},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6556409597396851},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.6138624548912048},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5634898543357849},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4673754572868347},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46391549706459045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44163233041763306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013128876686096},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3435731530189514},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1603","pdf_url":"https://www.aclweb.org/anthology/W17-1603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACL Workshop on Ethics in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1603","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1603","pdf_url":"https://www.aclweb.org/anthology/W17-1603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACL Workshop on Ethics in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740834240.pdf","grobid_xml":"https://content.openalex.org/works/W2740834240.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2021751150","https://openalex.org/W2251964473","https://openalex.org/W2511234952","https://openalex.org/W2573553457","https://openalex.org/W2574338499","https://openalex.org/W2577007061","https://openalex.org/W2577315723","https://openalex.org/W2596567068","https://openalex.org/W2750779823","https://openalex.org/W2751936342","https://openalex.org/W2912814679","https://openalex.org/W3024839386","https://openalex.org/W4297805164","https://openalex.org/W4301029487"],"related_works":["https://openalex.org/W2294677930","https://openalex.org/W2801905285","https://openalex.org/W2028846973","https://openalex.org/W2698935035","https://openalex.org/W2756635080","https://openalex.org/W249766449","https://openalex.org/W1504443673","https://openalex.org/W2230419033","https://openalex.org/W2086821603","https://openalex.org/W2354149895"],"abstract_inverted_index":{"We":[0,21,70],"present":[1],"results":[2],"on":[3,13,30,40,75,82],"a":[4,24,65],"quantitative":[5],"analysis":[6],"of":[7,18,27,55],"publications":[8,28,83],"in":[9],"the":[10,34,85],"NLP":[11,86],"domain":[12],"collecting,":[14],"publishing":[15],"and":[16],"availability":[17],"research":[19,91],"data.":[20],"find":[22,49],"that":[23,50],"wide":[25],"range":[26],"rely":[29],"data":[31,44,56],"crawled":[32],"from":[33,84],"web,":[35],"but":[36,88],"few":[37],"give":[38],"details":[39],"how":[41,76],"potentially":[42],"sensitive":[43],"was":[45],"treated.":[46],"Additionally,":[47],"we":[48],"while":[51],"links":[52],"to":[53,77],"repositories":[54],"are":[57],"given,":[58],"they":[59],"often":[60],"do":[61],"not":[62],"work":[63],"even":[64],"short":[66],"time":[67],"after":[68],"publication.":[69],"put":[71],"together":[72],"several":[73],"suggestions":[74],"improve":[78],"this":[79],"situation":[80],"based":[81],"domain,":[87],"also":[89],"other":[90],"areas.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
