{"id":"https://openalex.org/W3207654254","doi":null,"title":"EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks","display_name":"EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks","publication_year":2021,"publication_date":"2021-10-16","ids":{"openalex":"https://openalex.org/W3207654254","mag":"3207654254"},"language":"en","primary_location":{"id":"mag:3207654254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08426.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.08426.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015466440","display_name":"Frederick Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frederick Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034084374","display_name":"Siamak Shakeri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siamak Shakeri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433901","display_name":"Hongkun Yu","orcid":"https://orcid.org/0000-0002-2591-6328","observed_orcids":["https://orcid.org/0000-0002-2591-6328"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongkun Yu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2591-6328","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683044","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-3262-3734","observed_orcids":["https://orcid.org/0000-0002-3262-3734"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":"https://orcid.org/0000-0002-3262-3734","affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.986299991607666,"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":0.986299991607666,"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":0.008500000461935997,"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":0.002300000051036477,"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/t5","display_name":"T5","score":0.8370000123977661},{"id":"https://openalex.org/keywords/encoder-decoder-transformer","display_name":"transformer encoder-decoder","score":0.7099999785423279},{"id":"https://openalex.org/keywords/classification","display_name":"classification","score":0.5759999752044678},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"regression analysis","score":0.9929999709129333},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.7059999704360962},{"id":"https://openalex.org/keywords/glue-benchmark","display_name":"GLUE benchmark","score":0.7820000052452087},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.828000009059906}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8470948934555054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017550706863403},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6697058081626892},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6145071983337402},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6083993315696716},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5024149417877197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48140811920166016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4466260075569153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43989256024360657},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.42145949602127075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3642095923423767},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3569970726966858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33319807052612305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09881120920181274},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07793745398521423},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07135763764381409},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06530916690826416},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3207654254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08426.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3207654254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08426.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2885185669","https://openalex.org/W2900096133","https://openalex.org/W2950813464","https://openalex.org/W2962911098","https://openalex.org/W2963341956","https://openalex.org/W3001279689","https://openalex.org/W3030520226","https://openalex.org/W3082274269","https://openalex.org/W3169064633","https://openalex.org/W3169483174","https://openalex.org/W6893675597"],"related_works":["https://openalex.org/W4319988991","https://openalex.org/W4400459210","https://openalex.org/W4415335368","https://openalex.org/W3194782062","https://openalex.org/W4389519385","https://openalex.org/W4416120571","https://openalex.org/W4405311063","https://openalex.org/W4386557948","https://openalex.org/W7131827282","https://openalex.org/W4403063412"],"abstract_inverted_index":{"Encoder-decoder":[0],"transformer":[1],"architectures":[2,19],"have":[3],"become":[4],"popular":[5],"recently":[6],"with":[7,118],"the":[8,57,62,73,109,123],"advent":[9],"of":[10,122,125],"T5":[11,100,126,130],"models.":[12],"It":[13],"is":[14,53,61],"also":[15],"more":[16,50],"favorable":[17],"over":[18],"like":[20],"BERT":[21],"for":[22,65,102],"pre-training":[23],"on":[24,67,132],"language":[25],"model":[26],"task":[27],"when":[28],"it":[29,52],"comes":[30],"to":[31,39,47,49,95,129,144],"large":[32],"scale":[33],"models":[34,84,101,131],"which":[35],"could":[36],"take":[37],"months":[38],"train":[40],"given":[41,72],"it's":[42],"generality.":[43],"While":[44],"being":[45],"able":[46],"generalize":[48],"tasks,":[51],"not":[54],"evident":[55],"if":[56],"proposed":[58,138],"encoder-decoder":[59,83,99,147],"architecture":[60],"most":[63],"efficient":[64],"fine-tuning":[66,81],"classification":[68,103],"and":[69,104],"regression":[70,105],"tasks":[71,106],"pre-trained":[74,82,98,146],"model.":[75,148],"In":[76],"this":[77],"work,":[78],"we":[79,89],"study":[80],"such":[85],"as":[86,92],"T5.":[87],"Particularly,":[88],"propose":[90],"\\textbf{EncT5}":[91,117],"a":[93],"way":[94],"efficiently":[96],"fine-tune":[97],"by":[107],"using":[108],"encoder":[110],"layers.":[111],"Our":[112],"experimental":[113],"results":[114],"show":[115],"that":[116],"less":[119],"than":[120],"half":[121],"parameters":[124],"performs":[127],"similarly":[128],"GLUE":[133],"benchmark.":[134],"We":[135],"believe":[136],"our":[137],"approach":[139],"can":[140],"be":[141],"easily":[142],"applied":[143],"any":[145]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-25T00:00:00"}