{"id":"https://openalex.org/W2789202651","doi":"https://doi.org/10.1162/tacl_a_00008","title":"Evaluating the Stability of Embedding-based Word Similarities","display_name":"Evaluating the Stability of Embedding-based Word Similarities","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2789202651","doi":"https://doi.org/10.1162/tacl_a_00008","mag":"2789202651"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00008","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00008","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00008","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00008","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001225581","display_name":"Maria Antoniak","orcid":"https://orcid.org/0000-0002-4807-2850"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maria Antoniak","raw_affiliation_strings":["Cornell University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086934220","display_name":"David Mimno","orcid":"https://orcid.org/0000-0001-7510-9404"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Mimno","raw_affiliation_strings":["Cornell University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001225581","https://openalex.org/A5086934220"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":18.5846,"has_fulltext":true,"cited_by_count":221,"citation_normalized_percentile":{"value":0.99323382,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"107","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8457923531532288},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7636204957962036},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6972522735595703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6412343382835388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6140837073326111},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6109846830368042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5772698521614075},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.551315188407898},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5481895208358765},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46620118618011475},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.44123515486717224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23691460490226746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1917456090450287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457923531532288},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7636204957962036},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6972522735595703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6412343382835388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6140837073326111},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6109846830368042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5772698521614075},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.551315188407898},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5481895208358765},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46620118618011475},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.44123515486717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23691460490226746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1917456090450287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00008","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00008","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00008","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:656219a92fe54182a159f452f4cda040","is_oa":false,"landing_page_url":"https://doaj.org/article/656219a92fe54182a159f452f4cda040","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 6 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00008","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00008","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00008","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6046382484","display_name":null,"funder_award_id":"1526155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2789202651.pdf","grobid_xml":"https://content.openalex.org/works/W2789202651.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1480679540","https://openalex.org/W1503259811","https://openalex.org/W1615991656","https://openalex.org/W1662133657","https://openalex.org/W1880262756","https://openalex.org/W1955857676","https://openalex.org/W1983578042","https://openalex.org/W2102343050","https://openalex.org/W2117756735","https://openalex.org/W2125031621","https://openalex.org/W2135631383","https://openalex.org/W2141599568","https://openalex.org/W2147152072","https://openalex.org/W2158139315","https://openalex.org/W2250539671","https://openalex.org/W2250861254","https://openalex.org/W2251617662","https://openalex.org/W2252212383","https://openalex.org/W2254973503","https://openalex.org/W2292415828","https://openalex.org/W2294546627","https://openalex.org/W2349767596","https://openalex.org/W2483215953","https://openalex.org/W2512498397","https://openalex.org/W2557283755","https://openalex.org/W2574488981","https://openalex.org/W2606089314","https://openalex.org/W2739884042","https://openalex.org/W2963492501","https://openalex.org/W2963780471","https://openalex.org/W3158986179","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,22],"are":[2,31,45,80],"increasingly":[3],"being":[4],"used":[5],"as":[6],"a":[7,56],"tool":[8],"to":[9,33,48],"study":[10],"word":[11],"associations":[12],"in":[13,36,51,66,72],"specific":[14,64],"corpora.":[15,86,110],"However,":[16],"it":[17],"is":[18],"unclear":[19],"whether":[20],"such":[21],"reflect":[23],"enduring":[24],"properties":[25],"of":[26,58],"language":[27],"or":[28],"if":[29],"they":[30],"sensitive":[32,47],"inconsequential":[34],"variations":[35],"the":[37,52,67],"source":[38],"documents.":[39],"We":[40,75,87],"find":[41],"that":[42,77,89],"nearest-neighbor":[43],"distances":[44],"highly":[46],"small":[49,109],"changes":[50],"training":[53,68,85],"corpus":[54],"for":[55,83,97,108],"variety":[57],"algorithms.":[59],"For":[60],"all":[61],"methods,":[62],"including":[63],"documents":[65],"set":[69],"can":[70],"result":[71],"substantial":[73],"variations.":[74],"show":[76],"these":[78],"effects":[79],"more":[81],"prominent":[82],"smaller":[84],"recommend":[88],"users":[90],"never":[91],"rely":[92],"on":[93],"single":[94],"embedding":[95],"models":[96],"distance":[98],"calculations,":[99],"but":[100],"rather":[101],"average":[102],"over":[103],"multiple":[104],"bootstrap":[105],"samples,":[106],"especially":[107]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":10}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}