{"id":"https://openalex.org/W2966013379","doi":"https://doi.org/10.24963/ijcai.2019/477","title":"The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning","display_name":"The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966013379","doi":"https://doi.org/10.24963/ijcai.2019/477","mag":"2966013379"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/477","pdf_url":"https://www.ijcai.org/proceedings/2019/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0477.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102705831","display_name":"Bonggun Shin","orcid":"https://orcid.org/0000-0002-5133-0558"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bonggun Shin","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090632160","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0003-2214-9474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Visa Research, Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visa Research, Palo Alto, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101829031","display_name":"Jinho D. Choi","orcid":"https://orcid.org/0000-0003-2693-6934"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinho D. Choi","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0122,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82791072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3439","last_page":"3445"},"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":0.9994999766349792,"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":0.9936000108718872,"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":0.7585130929946899},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.72496497631073},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7097471952438354},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6796209216117859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5988147258758545},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5863146781921387},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.583074688911438},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5159311890602112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4975447952747345},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.48584648966789246},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.48520591855049133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42120489478111267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09491884708404541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585130929946899},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.72496497631073},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7097471952438354},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6796209216117859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5988147258758545},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5863146781921387},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.583074688911438},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5159311890602112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4975447952747345},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.48584648966789246},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.48520591855049133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42120489478111267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09491884708404541},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/477","pdf_url":"https://www.ijcai.org/proceedings/2019/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/477","pdf_url":"https://www.ijcai.org/proceedings/2019/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966013379.pdf","grobid_xml":"https://content.openalex.org/works/W2966013379.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W80079294","https://openalex.org/W1602122992","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2014902591","https://openalex.org/W2070246124","https://openalex.org/W2102409316","https://openalex.org/W2134797427","https://openalex.org/W2136933783","https://openalex.org/W2156413587","https://openalex.org/W2160660844","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2402089858","https://openalex.org/W2493916176","https://openalex.org/W2509386510","https://openalex.org/W2949380545","https://openalex.org/W2952186591","https://openalex.org/W2952822287","https://openalex.org/W2952899695","https://openalex.org/W2963703618","https://openalex.org/W4294170691","https://openalex.org/W4295364049","https://openalex.org/W4297813615"],"related_works":["https://openalex.org/W2794896638","https://openalex.org/W2891633941","https://openalex.org/W4286432911","https://openalex.org/W3202800081","https://openalex.org/W3101614107","https://openalex.org/W1909207154","https://openalex.org/W4390971112","https://openalex.org/W3036530763","https://openalex.org/W1514365828","https://openalex.org/W3149839747"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,39],"deep":[3],"learning":[4],"have":[5],"facilitated":[6],"the":[7,34,52,81,91,102,133],"demand":[8],"of":[9,36,54,144],"neural":[10,37,158],"models":[11,38,83,104,120,135],"for":[12,136],"real":[13],"applications.":[14],"In":[15,78],"practice,":[16],"these":[17],"applications":[18],"often":[19],"need":[20],"to":[21,154],"be":[22],"deployed":[23],"with":[24],"limited":[25],"resources":[26],"while":[27],"keeping":[28],"high":[29],"accuracy.":[30,59],"This":[31],"paper":[32],"touches":[33],"core":[35],"NLP,":[40],"word":[41,55,145],"embeddings,":[42],"and":[43,113,128,149],"presents":[44],"an":[45],"embedding":[46],"distillation":[47,62,148],"framework":[48],"that":[49,68,90],"remarkably":[50],"reduces":[51],"dimension":[53],"embeddings":[56,146],"without":[57,98],"compromising":[58],"A":[60],"new":[61],"ensemble":[63,155],"approach":[64],"is":[65],"also":[66],"proposed":[67],"trains":[69],"a":[70,151],"high-efficient":[71],"student":[72,92],"model":[73,93],"using":[74,157],"multiple":[75],"teacher":[76,82,103,134],"models.":[77,159],"our":[79],"approach,":[80],"play":[84],"roles":[85],"only":[86],"during":[87,105],"training":[88],"such":[89],"operates":[94],"on":[95,123],"its":[96],"own":[97],"getting":[99],"supports":[100],"from":[101,147],"decoding,":[106],"which":[107],"makes":[108],"it":[109],"run":[110],"as":[111,115],"fast":[112],"light":[114],"any":[116],"single":[117],"model.":[118],"All":[119],"are":[121],"evaluated":[122],"seven":[124],"document":[125],"classification":[126],"datasets":[127],"show":[129],"significant":[130],"advantage":[131],"over":[132],"most":[137],"cases.":[138],"Our":[139],"analysis":[140],"depicts":[141],"insightful":[142],"transformation":[143],"suggests":[150],"future":[152],"direction":[153],"approaches":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}