{"id":"https://openalex.org/W4200178892","doi":"https://doi.org/10.1109/hpec49654.2021.9622825","title":"Improved Compression for Word Embeddings by Scaling Principal Components","display_name":"Improved Compression for Word Embeddings by Scaling Principal Components","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200178892","doi":"https://doi.org/10.1109/hpec49654.2021.9622825"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004090802","display_name":"Joseph McDonald","orcid":"https://orcid.org/0009-0004-6477-8476"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph McDonald","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103227438","display_name":"Siddharth Samsi","orcid":"https://orcid.org/0009-0000-2884-9688"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Samsi","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037735778","display_name":"Daniel Edelman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Daniel Edelman","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087896681","display_name":"Chansup Byun","orcid":"https://orcid.org/0009-0003-0183-914X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chansup Byun","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108599","display_name":"Jeremy Kepner","orcid":"https://orcid.org/0000-0001-9668-2613"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Kepner","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043450560","display_name":"Vijay Gadepally","orcid":"https://orcid.org/0000-0002-4598-2808"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gadepally","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004090802"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57299149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"7"},"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":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/word2vec","display_name":"Word2vec","score":0.8710658550262451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8429886102676392},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6965548992156982},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6380075216293335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802415013313293},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5669202208518982},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5458697080612183},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5038694739341736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48129215836524963},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4810243248939514},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4303126335144043},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.42971378564834595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32140031456947327}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8710658550262451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429886102676392},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6965548992156982},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6380075216293335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802415013313293},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5669202208518982},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5458697080612183},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5038694739341736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48129215836524963},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4810243248939514},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4303126335144043},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.42971378564834595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32140031456947327},{"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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1491334865","https://openalex.org/W1503259811","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1854884267","https://openalex.org/W1992009922","https://openalex.org/W2026487812","https://openalex.org/W2081580037","https://openalex.org/W2112184938","https://openalex.org/W2117130368","https://openalex.org/W2125031621","https://openalex.org/W2163455955","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251044566","https://openalex.org/W2251939518","https://openalex.org/W2289952147","https://openalex.org/W2509386510","https://openalex.org/W2518186251","https://openalex.org/W2587690726","https://openalex.org/W2626970695","https://openalex.org/W2752172973","https://openalex.org/W2883672905","https://openalex.org/W2963558636","https://openalex.org/W2964232431","https://openalex.org/W2970959587","https://openalex.org/W2998704965","https://openalex.org/W3035762680","https://openalex.org/W3099432326","https://openalex.org/W3106525532","https://openalex.org/W4288118052","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6678885109","https://openalex.org/W6680532216","https://openalex.org/W6691444529","https://openalex.org/W6691459498","https://openalex.org/W6691746754","https://openalex.org/W6734040793","https://openalex.org/W6743384090","https://openalex.org/W6767421964"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W4382201653","https://openalex.org/W3107848922","https://openalex.org/W3133567596","https://openalex.org/W2798009317","https://openalex.org/W4312127319","https://openalex.org/W2998070955","https://openalex.org/W3175524270"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,77,114],"have":[2],"been":[3],"adopted":[4],"as":[5,79,100,102,107,157,159],"a":[6,27,40,164],"fundamental":[7],"component":[8],"of":[9,75,138,166],"many":[10],"natural":[11],"language":[12],"processing":[13],"applications":[14],"for":[15,43,141],"their":[16,48],"ability":[17],"to":[18,32,62,111,128],"capture":[19],"meaningful":[20],"semantic":[21,130],"relationships.":[22],"However":[23],"they":[24],"often":[25],"present":[26,39],"significant":[28],"computational":[29],"bottleneck":[30],"due":[31],"memory":[33,73,142],"requirements.":[34],"In":[35],"this":[36,119,153],"article":[37],"we":[38],"postprocessing":[41,117,161],"technique":[42,68],"embeddings,":[44],"based":[45],"on":[46,90,103,123],"modifying":[47],"principal":[49],"components,":[50],"that":[51],"enables":[52],"compression":[53],"while":[54,85],"maintaining":[55,86],"comparable":[56],"if":[57],"not":[58],"better":[59,129],"performance":[60,89,144],"relative":[61],"the":[63,71,87,112,148],"original":[64,113,149],"embedding.":[65],"Specifically,":[66],"our":[67],"can":[69],"reduce":[70],"overall":[72],"footprint":[74],"popular":[76],"such":[78,106],"GloVe":[80],"and":[81,97,115,126,143],"word2vec":[82],"by":[83],"50%":[84],"same":[88],"different":[91],"metrics,":[92],"including":[93],"commonly":[94],"used":[95],"similarity":[96],"analogy":[98],"tasks":[99,105,125],"well":[101,158],"end-to-end":[104],"text":[108],"classification.":[109],"Compared":[110],"previous":[116],"methods,":[118],"approach":[120,154],"improves":[121],"accuracy":[122],"these":[124,139,156],"leads":[127],"vector":[131],"representations":[132],"particularly":[133],"when":[134],"using":[135],"compressed":[136,167],"versions":[137],"vectors":[140,150],"savings.":[145],"While":[146],"compressing":[147],"is":[151],"possible,":[152],"outperforms":[155],"other":[160],"methods":[162],"across":[163],"range":[165],"sizes.":[168]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}