{"id":"https://openalex.org/W2736989307","doi":null,"title":"Word vectors, reuse, and replicability: Towards a community repository of large-text resources","display_name":"Word vectors, reuse, and replicability: Towards a community repository of large-text resources","publication_year":2017,"publication_date":"2017-05-08","ids":{"openalex":"https://openalex.org/W2736989307","mag":"2736989307"},"language":"en","primary_location":{"id":"pmh:oai:dspace.ut.ee:10062/92959","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/92959","pdf_url":"https://dspace.ut.ee/bitstreams/e8baa331-2894-45c0-8860-df20b79d5432/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.ut.ee/bitstreams/e8baa331-2894-45c0-8860-df20b79d5432/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058116024","display_name":"Murhaf Fares","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Murhaf Fares","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071409817","display_name":"Andrey Kutuzov","orcid":"https://orcid.org/0000-0003-2540-5912","observed_orcids":["https://orcid.org/0000-0003-2540-5912","https://orcid.org/0009-0004-6652-2968"]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Andrey Kutuzov","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2540-5912","affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058412010","display_name":"Stephan Oepen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Stephan Oepen","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080146945","display_name":"Erik Velldal","orcid":"https://orcid.org/0009-0008-6479-4512","observed_orcids":["https://orcid.org/0009-0008-6479-4512"]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Erik Velldal","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":10.8182,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":{"value":0.98848073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":"131","first_page":"271","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.98580002784729,"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":0.98580002784729,"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":0.008299999870359898,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0006000000284984708,"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/word-embeddings","display_name":"word embeddings","score":0.9879999756813049},{"id":"https://openalex.org/keywords/shared-repositories","display_name":"shared repositories","score":0.7210000157356262},{"id":"https://openalex.org/keywords/research-reuse","display_name":"research reuse","score":0.44999998807907104},{"id":"https://openalex.org/keywords/replicability","display_name":"replicability","score":0.8700000047683716},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6563543677330017},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6461449861526489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5928953886032104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4626634120941162},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4344116151332855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3244209885597229},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.150936096906662},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08257362246513367},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.07095497846603394}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:dspace.ut.ee:10062/92959","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/92959","pdf_url":"https://dspace.ut.ee/bitstreams/e8baa331-2894-45c0-8860-df20b79d5432/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"mag:2736989307","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/W17-0237.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306463555","display_name":"Link\u00f6ping University Electronic Press eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310317096","host_organization_name":"Link\u00f6ping University Electronic Press","host_organization_lineage":["https://openalex.org/P4310317096"],"host_organization_lineage_names":["Link\u00f6ping University Electronic Press"],"type":"ebook platform"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Link\u00f6ping University Electronic Press eBooks","raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.ut.ee:10062/92959","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/92959","pdf_url":"https://dspace.ut.ee/bitstreams/e8baa331-2894-45c0-8860-df20b79d5432/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2736989307.pdf","grobid_xml":"https://content.openalex.org/works/W2736989307.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W91323280","https://openalex.org/W168564468","https://openalex.org/W204849900","https://openalex.org/W1584739173","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1832693441","https://openalex.org/W1854884267","https://openalex.org/W1983578042","https://openalex.org/W2018985087","https://openalex.org/W2078483536","https://openalex.org/W2122056984","https://openalex.org/W2127041269","https://openalex.org/W2134036914","https://openalex.org/W2153579005","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2296283641","https://openalex.org/W2408306441","https://openalex.org/W2414012309","https://openalex.org/W2493916176","https://openalex.org/W2574488981","https://openalex.org/W2963216505","https://openalex.org/W2964090065"],"related_works":["https://openalex.org/W7110668027","https://openalex.org/W2251253014","https://openalex.org/W3153249702","https://openalex.org/W2758771122","https://openalex.org/W7098112573","https://openalex.org/W2788784374","https://openalex.org/W2252238828","https://openalex.org/W3119300200","https://openalex.org/W2780932362","https://openalex.org/W7024581106"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"emerging":[4],"shared":[5],"repository":[6],"of":[7,23,34],"large-text":[8],"resources":[9],"for":[10,20],"creating":[11],"word":[12],"vectors,":[13],"including":[14],"pre-processed":[15],"corpora":[16],"and":[17,25,32],"pre-trained":[18],"vectors":[19],"a":[21],"range":[22],"frameworks":[24],"configurations.This":[26],"will":[27],"facilitate":[28],"reuse,":[29],"rapid":[30],"experimentation,":[31],"replicability":[33],"results.":[35]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-07-31T00:00:00"}