{"id":"https://openalex.org/W2896232552","doi":"https://doi.org/10.18653/v1/p19-1315","title":"Towards Understanding Linear Word Analogies","display_name":"Towards Understanding Linear Word Analogies","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2896232552","doi":"https://doi.org/10.18653/v1/p19-1315","mag":"2896232552"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1315","pdf_url":"https://www.aclweb.org/anthology/P19-1315.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1315.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070411028","display_name":"Kawin Ethayarajh","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kawin Ethayarajh","raw_affiliation_strings":["Stanford University, Stanford, United States"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030409494","display_name":"David Duvenaud","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Duvenaud","raw_affiliation_strings":["Vector Institute","University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Vector Institute","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088047776","display_name":"Graeme Hirst","orcid":"https://orcid.org/0000-0001-9482-1042"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Graeme Hirst","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070411028"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.4335,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70295414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3253","last_page":"3262"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9968000054359436,"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","display_name":"Word (group theory)","score":0.7463898062705994},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.6518837213516235},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5856467485427856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.508148193359375},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4859501123428345},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43433475494384766},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4288240373134613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4243742525577545},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.41880184412002563},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.4140765368938446},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.39715176820755005},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.33278965950012207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28971049189567566},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.236407071352005}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7463898062705994},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.6518837213516235},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5856467485427856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508148193359375},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4859501123428345},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43433475494384766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4288240373134613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4243742525577545},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.41880184412002563},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.4140765368938446},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.39715176820755005},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.33278965950012207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28971049189567566},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.236407071352005},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1315","pdf_url":"https://www.aclweb.org/anthology/P19-1315.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.04882","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04882","pdf_url":"https://arxiv.org/pdf/1810.04882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2896232552","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.04882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1810.04882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.04882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1315","pdf_url":"https://www.aclweb.org/anthology/P19-1315.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2896232552.pdf","grobid_xml":"https://content.openalex.org/works/W2896232552.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1593045043","https://openalex.org/W1983578042","https://openalex.org/W2024932032","https://openalex.org/W2048176942","https://openalex.org/W2117130368","https://openalex.org/W2125031621","https://openalex.org/W2132339004","https://openalex.org/W2153579005","https://openalex.org/W2247359815","https://openalex.org/W2250539671","https://openalex.org/W2518186251","https://openalex.org/W2741613777","https://openalex.org/W2752172973","https://openalex.org/W2759848268","https://openalex.org/W2887005207","https://openalex.org/W2904759072","https://openalex.org/W2913433659","https://openalex.org/W2950577311","https://openalex.org/W2979401726"],"related_works":["https://openalex.org/W3094057833","https://openalex.org/W2984561976","https://openalex.org/W1984864392","https://openalex.org/W3162612541","https://openalex.org/W2950985971","https://openalex.org/W2971477168","https://openalex.org/W2766398264","https://openalex.org/W2951687440","https://openalex.org/W2436113537","https://openalex.org/W1710036787","https://openalex.org/W2167483151","https://openalex.org/W2971579914","https://openalex.org/W127619716","https://openalex.org/W2351251685","https://openalex.org/W2952070529","https://openalex.org/W2952388772","https://openalex.org/W2964794617","https://openalex.org/W3048860184","https://openalex.org/W2101961482","https://openalex.org/W2998706143"],"abstract_inverted_index":{"A":[0],"surprising":[1],"property":[2],"of":[3,41,98,125],"word":[4,8,59,100,136],"vectors":[5,101],"is":[6,19],"that":[7,49,70,86,104],"analogies":[9],"can":[10,79],"often":[11],"be":[12,80],"solved":[13],"with":[14,32],"vector":[15,56,75,129],"arithmetic.":[16],"However,":[17],"it":[18,105],"unclear":[20],"why":[21],"arithmetic":[22],"operators":[23],"correspond":[24],"to":[25],"non-linear":[26],"embedding":[27],"models":[28],"such":[29],"as":[30,82,112],"skip-gram":[31],"negative":[33],"sampling":[34],"(SGNS).":[35],"We":[36,91],"provide":[37,92],"a":[38],"formal":[39],"explanation":[40],"this":[42,87],"phenomenon":[43],"without":[44],"making":[45],"the":[46,55,96,108],"strong":[47],"assumptions":[48],"past":[50],"theories":[51],"have":[52],"made":[53],"about":[54],"space":[57],"and":[58],"distribution.":[60],"Our":[61],"theory":[62],"has":[63,68],"several":[64],"implications.":[65],"Past":[66],"work":[67],"conjectured":[69],"linear":[71],"substructures":[72],"exist":[73],"in":[74,128,134],"spaces":[76],"because":[77],"relations":[78],"represented":[81],"ratios;":[83],"we":[84,119],"prove":[85],"holds":[88],"for":[89,95],"SGNS.":[90],"novel":[93],"justification":[94],"addition":[97],"SGNS":[99],"by":[102],"showing":[103],"automatically":[106],"downweights":[107],"more":[109],"frequent":[110],"word,":[111],"weighting":[113],"schemes":[114],"do":[115],"ad":[116],"hoc.":[117],"Lastly,":[118],"offer":[120],"an":[121],"information":[122],"theoretic":[123],"interpretation":[124],"Euclidean":[126],"distance":[127],"spaces,":[130],"justifying":[131],"its":[132],"use":[133],"capturing":[135],"dissimilarity.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}