{"id":"https://openalex.org/W2977321685","doi":"https://doi.org/10.1162/tacl_a_00289","title":"Efficient Contextual Representation Learning With Continuous Outputs","display_name":"Efficient Contextual Representation Learning With Continuous Outputs","publication_year":2019,"publication_date":"2019-09-30","ids":{"openalex":"https://openalex.org/W2977321685","doi":"https://doi.org/10.1162/tacl_a_00289","mag":"2977321685"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00289","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00289","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00289/1923656/tacl_a_00289.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00289/1923656/tacl_a_00289.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004824034","display_name":"Liunian Harold Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liunian Harold Li","raw_affiliation_strings":["Peking University","Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075080451","display_name":"Patrick H. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrick H. Chen","raw_affiliation_strings":["University of California, Los Angeles","University of California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["University of California, Los Angeles","University of California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles","University of California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004824034","https://openalex.org/A5010841999","https://openalex.org/A5075080451","https://openalex.org/A5087096372"],"corresponding_institution_ids":["https://openalex.org/I161318765","https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.951,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82278094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"611","last_page":"624"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.8955512046813965},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7807300686836243},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6641845703125},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6023825407028198},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.599331259727478},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5879812240600586},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5805211067199707},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5650704503059387},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5513524413108826},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5167771577835083},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4987492561340332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4960666596889496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.468959242105484},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4409295320510864},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42990541458129883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38096022605895996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3594658374786377},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22963273525238037},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09302195906639099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955512046813965},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7807300686836243},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6641845703125},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6023825407028198},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.599331259727478},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5879812240600586},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5805211067199707},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5650704503059387},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5513524413108826},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5167771577835083},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4987492561340332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960666596889496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.468959242105484},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4409295320510864},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42990541458129883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38096022605895996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3594658374786377},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22963273525238037},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09302195906639099},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00289","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00289","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00289/1923656/tacl_a_00289.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fc937d69386f4ba3bd778703ad2592c5","is_oa":true,"landing_page_url":"https://doaj.org/article/fc937d69386f4ba3bd778703ad2592c5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 7, Pp 611-624 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00289","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00289","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00289/1923656/tacl_a_00289.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4385247538","display_name":"CRII: RI: Learning Structured Prediction Models with Auxiliary Supervision","funder_award_id":"1760523","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8147927977","display_name":"RI: SMALL: Fast Prediction and Model Compression for Large-Scale Machine Learning","funder_award_id":"1901527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2977321685.pdf","grobid_xml":"https://content.openalex.org/works/W2977321685.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W1558797106","https://openalex.org/W1581231885","https://openalex.org/W1840435438","https://openalex.org/W1938755728","https://openalex.org/W2064675550","https://openalex.org/W2103076621","https://openalex.org/W2120861206","https://openalex.org/W2125031621","https://openalex.org/W2144578941","https://openalex.org/W2146502635","https://openalex.org/W2155069789","https://openalex.org/W2158899491","https://openalex.org/W2251939518","https://openalex.org/W2259472270","https://openalex.org/W2427527485","https://openalex.org/W2519314406","https://openalex.org/W2525778437","https://openalex.org/W2608787653","https://openalex.org/W2610858497","https://openalex.org/W2622263826","https://openalex.org/W2740765036","https://openalex.org/W2780932362","https://openalex.org/W2787560479","https://openalex.org/W2788510939","https://openalex.org/W2792376130","https://openalex.org/W2793978524","https://openalex.org/W2798304389","https://openalex.org/W2806042905","https://openalex.org/W2888329843","https://openalex.org/W2896060389","https://openalex.org/W2904683980","https://openalex.org/W2908475389","https://openalex.org/W2948223045","https://openalex.org/W2950577311","https://openalex.org/W2950726992","https://openalex.org/W2951714314","https://openalex.org/W2952436057","https://openalex.org/W2962747323","https://openalex.org/W2962784628","https://openalex.org/W2963037202","https://openalex.org/W2963087868","https://openalex.org/W2963174729","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963421945","https://openalex.org/W2963537482","https://openalex.org/W2963644595","https://openalex.org/W2963756346","https://openalex.org/W2963970792","https://openalex.org/W2964045208","https://openalex.org/W2964222246","https://openalex.org/W3023058184","https://openalex.org/W3037932933"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W2058965144","https://openalex.org/W3022820045","https://openalex.org/W1773599773","https://openalex.org/W2268150819"],"abstract_inverted_index":{"Contextual":[0],"representation":[1],"models":[2],"have":[3],"achieved":[4],"great":[5],"success":[6],"in":[7],"improving":[8],"various":[9,122],"downstream":[10,109],"natural":[11],"language":[12],"processing":[13],"tasks.":[14,110],"However,":[15],"these":[16],"language-model-based":[17],"encoders":[18],"are":[19],"difficult":[20],"to":[21,24,90],"train":[22],"due":[23],"their":[25],"large":[26],"parameter":[27],"size":[28,61],"and":[29,73,99],"high":[30],"computational":[31],"complexity.":[32],"By":[33],"carefully":[34],"examining":[35],"the":[36,42,50,59,67,70,77,81,92,115,118,126],"training":[37],"procedure,":[38],"we":[39,65],"observe":[40],"that":[41,114],"softmax":[43],"layer,":[44],"which":[45],"predicts":[46],"a":[47,85,96],"distribution":[48],"of":[49,69,80],"target":[51,82],"word,":[52],"often":[53],"induces":[54],"significant":[55],"overhead,":[56],"especially":[57],"when":[58,125],"vocabulary":[60],"is":[62,129],"large.":[63],"Therefore,":[64],"revisit":[66],"design":[68],"output":[71],"layer":[72],"consider":[74],"directly":[75],"predicting":[76],"pre-trained":[78],"embedding":[79],"word":[83],"for":[84],"given":[86],"context.":[87],"When":[88],"applied":[89],"ELMo,":[91],"proposed":[93],"approach":[94,116],"achieves":[95],"4-fold":[97],"speedup":[98],"eliminates":[100],"80%":[101],"trainable":[102],"parameters":[103],"while":[104],"achieving":[105],"competitive":[106],"performance":[107],"on":[108],"Further":[111],"analysis":[112],"shows":[113],"maintains":[117],"speed":[119],"advantage":[120],"under":[121],"settings,":[123],"even":[124],"sentence":[127],"encoder":[128],"scaled":[130],"up.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}