{"id":"https://openalex.org/W2740553347","doi":"https://doi.org/10.18653/v1/p17-2026","title":"Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function","display_name":"Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740553347","doi":"https://doi.org/10.18653/v1/p17-2026","mag":"2740553347"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2026","pdf_url":"https://www.aclweb.org/anthology/P17-2026.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2026.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089409089","display_name":"Oren Melamud","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Oren Melamud","raw_affiliation_strings":["IBM Research Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Faculty of Engineering Bar-Ilan University, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089409089"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5724,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82887616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12261","display_name":"Statistical Mechanics and Entropy","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6484265327453613},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6208557486534119},{"id":"https://openalex.org/keywords/marginal-distribution","display_name":"Marginal distribution","score":0.5752028226852417},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.547700822353363},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5294228196144104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5176606774330139},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.47608938813209534},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.46053245663642883},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.443628191947937},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.44318264722824097},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.44055530428886414},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.43203413486480713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4212421178817749},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.38180893659591675},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3633432984352112},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34056830406188965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382282257080078},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1993291676044464}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6484265327453613},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6208557486534119},{"id":"https://openalex.org/C165216359","wikidata":"https://www.wikidata.org/wiki/Q670653","display_name":"Marginal distribution","level":3,"score":0.5752028226852417},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.547700822353363},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5294228196144104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5176606774330139},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47608938813209534},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.46053245663642883},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.443628191947937},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.44318264722824097},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.44055530428886414},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.43203413486480713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4212421178817749},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.38180893659591675},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3633432984352112},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34056830406188965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382282257080078},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1993291676044464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-2026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2026","pdf_url":"https://www.aclweb.org/anthology/P17-2026.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2026","pdf_url":"https://www.aclweb.org/anthology/P17-2026.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326823","display_name":"Intel Collaboration Research Institute for Computational Intelligence","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740553347.pdf","grobid_xml":"https://content.openalex.org/works/W2740553347.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1615991656","https://openalex.org/W1686946872","https://openalex.org/W2004026774","https://openalex.org/W2125031621","https://openalex.org/W2135029798","https://openalex.org/W2146950091","https://openalex.org/W2153579005","https://openalex.org/W2250508463","https://openalex.org/W2250539671","https://openalex.org/W2251874715","https://openalex.org/W2518186251","https://openalex.org/W2964266863","https://openalex.org/W2979454998","https://openalex.org/W3006431365","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2383655479","https://openalex.org/W3094338031","https://openalex.org/W2031077553","https://openalex.org/W4243325142","https://openalex.org/W162901985","https://openalex.org/W2113818258","https://openalex.org/W2384643754","https://openalex.org/W4249404085","https://openalex.org/W2384407477","https://openalex.org/W4254087222"],"abstract_inverted_index":{"In":[0],"this":[1,47],"paper,":[2],"we":[3,31],"define":[4],"a":[5,70],"measure":[6,50],"of":[7,26,46],"dependency":[8,49],"between":[9,19,51,59],"two":[10],"random":[11],"variables,":[12],"based":[13],"on":[14,69],"the":[15,24,42,52,60,64],"Jensen-Shannon":[16],"(JS)":[17],"divergence":[18],"their":[20,27,55],"joint":[21],"distribution":[22],"and":[23,54,63],"product":[25],"marginal":[28],"distributions.":[29],"Then,":[30],"show":[32],"that":[33],"word2vec's":[34],"skip-gram":[35],"with":[36],"negative":[37],"sampling":[38],"embedding":[39],"algorithm":[40],"finds":[41],"optimal":[43,61],"low-dimensional":[44,65],"approximation":[45,66],"JS":[48],"words":[53],"contexts.":[56],"The":[57],"gap":[58],"score":[62],"is":[67],"demonstrated":[68],"standard":[71],"text":[72],"corpus.":[73]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}