{"id":"https://openalex.org/W3212497063","doi":"https://doi.org/10.1109/taslp.2021.3125133","title":"Subword-Based Compact Reconstruction for Open-Vocabulary Neural Word Embeddings","display_name":"Subword-Based Compact Reconstruction for Open-Vocabulary Neural Word Embeddings","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3212497063","doi":"https://doi.org/10.1109/taslp.2021.3125133","mag":"3212497063"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3125133","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125133","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2021.3125133","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040233526","display_name":"Shota Sasaki","orcid":"https://orcid.org/0000-0001-8070-9041"},"institutions":[{"id":"https://openalex.org/I4210165842","display_name":"RIKEN Center for Advanced Photonics","ror":"https://ror.org/05vmjks78","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210165842"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shota Sasaki","raw_affiliation_strings":["RIKEN, 13593 Sendai, Miyagi, Japan, 9808579 (e-mail: shota.sasaki.yv@riken.jp)"],"affiliations":[{"raw_affiliation_string":"RIKEN, 13593 Sendai, Miyagi, Japan, 9808579 (e-mail: shota.sasaki.yv@riken.jp)","institution_ids":["https://openalex.org/I4210165842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002182453","display_name":"Jun Suzuki","orcid":"https://orcid.org/0000-0003-2108-1340"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]},{"id":"https://openalex.org/I4210138310","display_name":"Tohoku Medical and Pharmaceutical University Hospital","ror":"https://ror.org/03ywrrr62","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210138310","https://openalex.org/I85324120"]},{"id":"https://openalex.org/I103605164","display_name":"Tohoku Institute of Technology","ror":"https://ror.org/01phqre83","country_code":"JP","type":"education","lineage":["https://openalex.org/I103605164"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Suzuki","raw_affiliation_strings":["Tohoku University, 13101 Sendai, Miyagi, Japan, (e-mail: jun.suzuki@ecei.tohoku.ac.jp)"],"affiliations":[{"raw_affiliation_string":"Tohoku University, 13101 Sendai, Miyagi, Japan, (e-mail: jun.suzuki@ecei.tohoku.ac.jp)","institution_ids":["https://openalex.org/I201537933","https://openalex.org/I4210138310","https://openalex.org/I103605164"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101815181","display_name":"Kentaro Inui","orcid":"https://orcid.org/0000-0001-6510-604X"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Inui","raw_affiliation_strings":["Tohoku University, Sendai, Miyagi, Japan, (e-mail: inui@ecei.tohoku.ac.jp)"],"affiliations":[{"raw_affiliation_string":"Tohoku University, Sendai, Miyagi, Japan, (e-mail: inui@ecei.tohoku.ac.jp)","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040233526"],"corresponding_institution_ids":["https://openalex.org/I4210165842"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73390822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"29","issue":null,"first_page":"3551","last_page":"3564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9932000041007996,"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":0.8370069265365601},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.816189169883728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6477370858192444},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5929769277572632},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5841062068939209},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5833157896995544},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5058495998382568},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46454310417175293},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4423179626464844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4188946783542633},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4143722653388977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32987475395202637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07871967554092407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370069265365601},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.816189169883728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6477370858192444},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5929769277572632},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5841062068939209},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5833157896995544},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5058495998382568},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46454310417175293},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4423179626464844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4188946783542633},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4143722653388977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32987475395202637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07871967554092407},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3125133","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125133","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3125133","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125133","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1840435438","https://openalex.org/W1854884267","https://openalex.org/W2026487812","https://openalex.org/W2064675550","https://openalex.org/W2080100102","https://openalex.org/W2103318667","https://openalex.org/W2112184938","https://openalex.org/W2141599568","https://openalex.org/W2164019165","https://openalex.org/W2170682101","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2493916176","https://openalex.org/W2574772032","https://openalex.org/W2608787653","https://openalex.org/W2621404689","https://openalex.org/W2756999401","https://openalex.org/W2798921788","https://openalex.org/W2799190973","https://openalex.org/W2877801623","https://openalex.org/W2891680269","https://openalex.org/W2896457183","https://openalex.org/W2952087486","https://openalex.org/W2962739339","https://openalex.org/W2962788148","https://openalex.org/W2963049082","https://openalex.org/W2963357517","https://openalex.org/W2963421945","https://openalex.org/W2963956670","https://openalex.org/W2964096343","https://openalex.org/W2964179002","https://openalex.org/W2998554035","https://openalex.org/W3035488502","https://openalex.org/W3099023595","https://openalex.org/W4246054309","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6636510571","https://openalex.org/W6680890276","https://openalex.org/W6682691769","https://openalex.org/W6684165356","https://openalex.org/W6691746754","https://openalex.org/W6731916224","https://openalex.org/W6739151214","https://openalex.org/W6739901393","https://openalex.org/W6752741978","https://openalex.org/W6755207826","https://openalex.org/W6764288440"],"related_works":["https://openalex.org/W2374192425","https://openalex.org/W1963734729","https://openalex.org/W2126560900","https://openalex.org/W4290056478","https://openalex.org/W2050755277","https://openalex.org/W1583489134","https://openalex.org/W2101627487","https://openalex.org/W2101346879","https://openalex.org/W2117523216","https://openalex.org/W2062636460"],"abstract_inverted_index":{"The":[0,117],"methodology":[1],"of":[2,70,83,99,120,130,170,178],"neural":[3,43],"word":[4,44,59,86,115,142,148],"embeddings":[5,45,87,101,126,143,149,169],"has":[6],"become":[7],"an":[8],"important":[9],"fundamental":[10],"resource":[11],"for":[12],"tackling":[13],"many":[14],"applications":[15],"in":[16,35,102,150],"the":[17,62,68,113,131,176],"artificial":[18],"intelligence":[19],"(AI)":[20],"research":[21],"field.":[22],"They":[23],"have":[24,46],"successfully":[25,145],"been":[26],"proven":[27],"to":[28,186],"capture":[29],"high-quality":[30],"syntactic":[31],"and":[32,66,127,164,194],"semantic":[33],"relationships":[34],"a":[36,81,96,103,128,151],"vector":[37],"space.":[38],"Despite":[39],"their":[40],"significant":[41],"impact,":[42],"several":[47,160],"disadvantages.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,79],"focus":[53],"on":[54],"two":[55,77],"issues":[56],"regarding":[57],"well-trained":[58,147],"embeddings:":[60],"(i)":[61],"massive":[63],"memory":[64],"requirement":[65],"(ii)":[67],"inapplicability":[69],"out-of-vocabulary":[71],"(OOV)":[72],"words.":[73,172],"To":[74],"overcome":[75],"these":[76],"issues,":[78],"propose":[80],"method":[82,122,181],"reconstructing":[84],"pre-trained":[85],"by":[88],"using":[89],"subword":[90,100],"information":[91],"that":[92,138],"can":[93,144,165],"effectively":[94],"represent":[95],"large":[97],"number":[98],"considerably":[104],"small":[105,152],"fixed":[106,153],"space":[107,154],"while":[108,155],"preventing":[109,156],"quality":[110,157],"degradation":[111,158],"from":[112],"original":[114],"embeddings.":[116],"key":[118],"techniques":[119],"our":[121,139,179],"are":[123],"twofold:":[124],"memory-shared":[125],"variant":[129],"key-value-query":[132],"self-attention":[133],"mechanism.":[134],"Our":[135],"experiments":[136],"show":[137],"reconstructed":[140],"subword-based":[141],"imitate":[146],"across":[159],"linguistic":[161],"benchmark":[162],"datasets":[163],"simultaneously":[166],"predict":[167],"effective":[168],"OOV":[171],"We":[173],"also":[174],"demonstrate":[175],"effectiveness":[177],"reconstruction":[180],"when":[182],"it":[183],"is":[184],"applied":[185],"downstream":[187],"tasks,":[188],"such":[189],"as":[190],"named":[191],"entity":[192],"recognition":[193],"natural":[195],"language":[196],"inference":[197],"tasks.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}