乐胖代购免代理版

{"id":"https://openalex.org/W4386566428","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.181","title":"Transformers with Learnable Activation Functions","display_name":"Transformers with Learnable Activation Functions","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386566428","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.181"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.181","pdf_url":"https://aclanthology.org/2023.findings-eacl.181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-eacl.181.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028344155","display_name":"Haishuo Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Haishuo Fang","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www."],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www.","institution_ids":["https://openalex.org/I16718484","https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081951157","display_name":"Ji-Ung Lee","orcid":"https://orcid.org/0000-0002-8428-2003"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Ji-Ung Lee","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www."],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www.","institution_ids":["https://openalex.org/I16718484","https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054918343","display_name":"Nafise Sadat Moosavi","orcid":"https://orcid.org/0000-0002-8332-307X"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["DE","GB","US"],"is_corresponding":false,"raw_author_name":"Nafise Sadat Moosavi","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield","Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www."],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www.","institution_ids":["https://openalex.org/I16718484","https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www."],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt www.","institution_ids":["https://openalex.org/I16718484","https://openalex.org/I31512782"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.057,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":3,"citation_normalized_percentile":{"value":0.999976,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":85,"max":88},"biblio":{"volume":null,"issue":null,"first_page":"2382","last_page":"2398"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9999,"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":0.9999,"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":0.999,"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":0.9964,"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/benchmark","display_name":"Benchmark (surveying)","score":0.43887773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725664},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.70005363},{"id":"https://openalex.org/C75190567","wikidata":"https://www.wikidata.org/wiki/Q41237","display_name":"Rational function","level":2,"score":0.44933766},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43887773},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42745999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3413837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16000053},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.101552874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.089594394},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0781661},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07409775},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.181","pdf_url":"https://aclanthology.org/2023.findings-eacl.181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/199941/1/2208.14111v1.pdf","pdf_url":"https://eprints.whiterose.ac.uk/199941/1/2208.14111v1.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":["White Rose University Consortium"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/199095/1/2023.findings-eacl.181.pdf","pdf_url":"https://eprints.whiterose.ac.uk/199095/1/2023.findings-eacl.181.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":["White Rose University Consortium"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2208.14111","pdf_url":"https://arxiv.org/pdf/2208.14111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.181","pdf_url":"https://aclanthology.org/2023.findings-eacl.181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.57,"display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":55,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1599016936","https://openalex.org/W1840435438","https://openalex.org/W2058568633","https://openalex.org/W2130158090","https://openalex.org/W2251939518","https://openalex.org/W2462831000","https://openalex.org/W2567070169","https://openalex.org/W2899675781","https://openalex.org/W2908510526","https://openalex.org/W2923014074","https://openalex.org/W2951104886","https://openalex.org/W2963339397","https://openalex.org/W2963341956","https://openalex.org/W2963347649","https://openalex.org/W2963582035","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2973727699","https://openalex.org/W2978670439","https://openalex.org/W2996428491","https://openalex.org/W3034999214","https://openalex.org/W3035035250","https://openalex.org/W3038944566","https://openalex.org/W3042896572","https://openalex.org/W3092448486","https://openalex.org/W3103368673","https://openalex.org/W3104033643","https://openalex.org/W3106331693","https://openalex.org/W3122890974","https://openalex.org/W3128090102","https://openalex.org/W3132956762","https://openalex.org/W3135427360","https://openalex.org/W3176828726","https://openalex.org/W3213305054","https://openalex.org/W4205694016","https://openalex.org/W4206136559","https://openalex.org/W4221167110","https://openalex.org/W4225591000","https://openalex.org/W4226102207","https://openalex.org/W4226399820","https://openalex.org/W4229005866","https://openalex.org/W4283791586","https://openalex.org/W4287815523","https://openalex.org/W4287824654","https://openalex.org/W4287855051","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4294808066","https://openalex.org/W4301581299","https://openalex.org/W4320930577","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W972276598","https://openalex.org/W915438175","https://openalex.org/W4321353415","https://openalex.org/W4246352526","https://openalex.org/W2745001401","https://openalex.org/W2378211422","https://openalex.org/W2130974462","https://openalex.org/W2121910908","https://openalex.org/W2086519370","https://openalex.org/W2028665553"],"abstract_inverted_index":{"Activation":[0],"functions":[1,26,43,70,78,85,95],"can":[2],"have":[3],"a":[4,18,37,108,165],"significant":[5],"impact":[6,67],"on":[7,71,123,140],"reducing":[8],"the":[9,22,66,92,102,124,147,150],"topological":[10],"complexity":[11],"of":[12,24,68,90,149],"input":[13],"data":[14],"and":[15,53,136,161,171],"therefore,":[16],"improving":[17],"model\u2019s":[19],"performance.":[20],"However,":[21],"choice":[23],"activation":[25,42,69,77,84,94],"is":[27],"seldom":[28],"discussed":[29],"or":[30],"explored":[31],"in":[32],"Transformer-based":[33,72],"language":[34,175],"models.":[35,176],"As":[36],"common":[38],"practice,":[39],"commonly":[40],"used":[41],"like":[44],"Gaussian":[45],"Error":[46],"Linear":[47],"Unit":[48],"(GELU)":[49],"are":[50,88],"chosen":[51],"beforehand":[52],"then":[54],"remain":[55],"fixed":[56,83],"from":[57,96],"pre-training":[58],"to":[59,82,168],"fine-tuning.":[60],"In":[61,80],"this":[62],"paper,":[63],"we":[64,118],"investigate":[65],"models":[73],"by":[74,127,137],"utilizing":[75],"rational":[76],"(RAFs).":[79],"contrast":[81],"(FAF),":[86],"RAFs":[87,152],"capable":[89],"learning":[91],"optimal":[93],"data.":[97,145],"Our":[98],"experiments":[99],"show":[100],"that":[101,120,155],"RAF-based":[103],"Transformer":[104],"model":[105],"(RAFT)":[106],"achieves":[107],"better":[109,169],"performance":[110],"than":[111],"its":[112],"FAF-based":[113],"counterpart":[114],"().":[115],"For":[116],"instance,":[117],"find":[119],"RAFT":[121],"outperforms":[122],"GLUE":[125],"benchmark":[126],"5.71":[128],"points":[129,139],"when":[130],"using":[131],"only":[132],"100":[133],"training":[134],"examples":[135],"2.05":[138],"SQuAD":[141],"with":[142],"all":[143],"available":[144],"Analyzing":[146],"shapes":[148],"learned":[151],"further":[153],"unveils":[154],"they":[156],"vary":[157],"across":[158],"different":[159,162],"layers":[160],"tasks;":[163],"opening":[164],"promising":[166],"way":[167],"analyze":[170],"understand":[172],"large,":[173],"pre-trained":[174]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4386566428","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2024-12-10T13:47:01.201741","created_date":"2023-09-10"}