{"id":"https://openalex.org/W2988022164","doi":"https://doi.org/10.18653/v1/d19-6122","title":"Natural Language Generation for Effective Knowledge Distillation","display_name":"Natural Language Generation for Effective Knowledge Distillation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2988022164","doi":"https://doi.org/10.18653/v1/d19-6122","mag":"2988022164"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6122","pdf_url":"https://www.aclweb.org/anthology/D19-6122.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6122.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101066425","display_name":"Raphael Tang","orcid":"https://orcid.org/0009-0007-2873-892X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raphael Tang","raw_affiliation_strings":["School of Computer Science University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Waterloo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026907508","display_name":"Yao Lu","orcid":"https://orcid.org/0000-0002-9873-8753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Lu","raw_affiliation_strings":["School of Computer Science University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Waterloo","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["School of Computer Science University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Waterloo","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"208"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8334538340568542},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7217589020729065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7174887657165527},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6273772716522217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6080184578895569},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.566760778427124},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5449835062026978},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5408004522323608},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.509881854057312},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4773426353931427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47296637296676636},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4544348120689392},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4486598074436188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4471653401851654},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4281005561351776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334538340568542},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7217589020729065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7174887657165527},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6273772716522217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6080184578895569},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.566760778427124},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5449835062026978},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5408004522323608},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.509881854057312},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4773426353931427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47296637296676636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4544348120689392},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4486598074436188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4471653401851654},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4281005561351776},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6122","pdf_url":"https://www.aclweb.org/anthology/D19-6122.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6122","pdf_url":"https://www.aclweb.org/anthology/D19-6122.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"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/W2988022164.pdf","grobid_xml":"https://content.openalex.org/works/W2988022164.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W131533222","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1832693441","https://openalex.org/W2064675550","https://openalex.org/W2134797427","https://openalex.org/W2142972908","https://openalex.org/W2251939518","https://openalex.org/W2586850891","https://openalex.org/W2606347107","https://openalex.org/W2784823820","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2924902521","https://openalex.org/W2932970397","https://openalex.org/W2962739339","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963494889","https://openalex.org/W2963574252","https://openalex.org/W2963840100","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2978670439","https://openalex.org/W3104033643","https://openalex.org/W4298422451","https://openalex.org/W4313908941"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3201126466","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,41],"can":[2],"effectively":[3],"transfer":[4,49,58,83],"knowledge":[5,54],"from":[6,65],"BERT,":[7],"a":[8,119,130],"deep":[9,120],"language":[10,30,67],"representation":[11,31],"model,":[12],"to":[13,39,63],"traditional,":[14],"shallow":[15],"word":[16],"embedding-based":[17],"neural":[18],"networks,":[19],"helping":[20],"them":[21],"approach":[22,91,110],"or":[23],"exceed":[24],"the":[25,44,79,82,126],"quality":[26],"of":[27,46,81,125],"other":[28],"heavyweight":[29],"models.":[32],"As":[33],"shown":[34],"in":[35,98],"previous":[36,74,113],"work,":[37],"critical":[38],"this":[40,76,88],"procedure":[42],"is":[43],"construction":[45],"an":[47],"unlabeled":[48],"dataset,":[50],"which":[51],"enables":[52],"effective":[53],"transfer.":[55],"To":[56],"create":[57],"set":[59],"examples,":[60],"we":[61,106],"propose":[62],"sample":[64],"pretrained":[66,121],"models":[68],"fine-tuned":[69],"on":[70,123],"taskspecific":[71],"text.":[72],"Unlike":[73],"techniques,":[75],"directly":[77],"captures":[78],"purpose":[80],"set.":[84],"We":[85,115],"hypothesize":[86],"that":[87,108,134],"principled,":[89],"general":[90],"outperforms":[92],"rule-based":[93],"techniques.":[94],"On":[95],"four":[96],"datasets":[97],"sentiment":[99],"classification,":[100],"sentence":[101],"similarity,":[102],"and":[103],"linguistic":[104],"acceptability,":[105],"show":[107],"our":[109],"improves":[111],"upon":[112],"methods.":[114],"outperform":[116],"OpenAI":[117],"GPT,":[118],"transformer,":[122],"three":[124],"datasets,":[127],"while":[128],"using":[129],"single-layer":[131],"bidirectional":[132],"LSTM":[133],"runs":[135],"at":[136],"least":[137],"ten":[138],"times":[139],"faster.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":16}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}