{"id":"https://openalex.org/W4386576812","doi":"https://doi.org/10.18653/v1/2023.eacl-main.273","title":"The NLP Task Effectiveness of Long-Range Transformers","display_name":"The NLP Task Effectiveness of Long-Range Transformers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386576812","doi":"https://doi.org/10.18653/v1/2023.eacl-main.273"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.eacl-main.273","doi":"https://doi.org/10.18653/v1/2023.eacl-main.273","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.eacl-main.273","pdf_url":"https://aclanthology.org/2023.eacl-main.273.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.eacl-main.273.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010680967","display_name":"Guanghui Qin","orcid":"https://orcid.org/0000-0002-3009-8614","observed_orcids":["https://orcid.org/0000-0002-3009-8614"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanghui Qin","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101199919","display_name":"Yukun Feng","orcid":"https://orcid.org/0009-0002-5467-5954","observed_orcids":["https://orcid.org/0009-0002-5467-5954"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Feng","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075825791","display_name":"Benjamin Van Durme","orcid":"https://orcid.org/0000-0003-4328-4288","observed_orcids":["https://orcid.org/0000-0003-4328-4288"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin Van Durme","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075825791"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.6068,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93132305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3774","last_page":"3790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9452999830245972,"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":0.9452999830245972,"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":0.036400001496076584,"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":0.0035000001080334187,"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/long-range-attention","display_name":"long-range attention","score":0.8939999938011169},{"id":"https://openalex.org/keywords/longformer","display_name":"Longformer","score":0.9079999923706055},{"id":"https://openalex.org/keywords/performing-artists","display_name":"performers","score":0.9959999918937683},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.48500001430511475},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.42399999499320984},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5680000185966492},{"id":"https://openalex.org/keywords/hyperparameter-settings","display_name":"hyperparameter settings","score":0.9229999780654907},{"id":"https://openalex.org/keywords/content-selection","display_name":"content selection","score":0.6669999957084656},{"id":"https://openalex.org/keywords/approximation-error","display_name":"approximation error","score":0.75}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8656162619590759},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7650266885757446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052837610244751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5466994047164917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298264622688293},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45843252539634705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4454527497291565},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4130796492099762},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3702716827392578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12355166673660278},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.eacl-main.273","doi":"https://doi.org/10.18653/v1/2023.eacl-main.273","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.eacl-main.273","pdf_url":"https://aclanthology.org/2023.eacl-main.273.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.07856","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.07856","pdf_url":"https://arxiv.org/pdf/2202.07856","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2202.07856","doi":"https://doi.org/10.48550/arxiv.2202.07856","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.07856","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.eacl-main.273","doi":"https://doi.org/10.18653/v1/2023.eacl-main.273","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.eacl-main.273","pdf_url":"https://aclanthology.org/2023.eacl-main.273.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386576812.pdf","grobid_xml":"https://content.openalex.org/works/W4386576812.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1965693266","https://openalex.org/W2154652894","https://openalex.org/W2169393322","https://openalex.org/W2612431505","https://openalex.org/W2626778328","https://openalex.org/W2793978524","https://openalex.org/W2950813464","https://openalex.org/W2962753370","https://openalex.org/W2963748441","https://openalex.org/W2963929190","https://openalex.org/W2964110616","https://openalex.org/W2964159778","https://openalex.org/W2969605360","https://openalex.org/W2979826702","https://openalex.org/W2986922898","https://openalex.org/W2994673210","https://openalex.org/W2997517014","https://openalex.org/W3006983028","https://openalex.org/W3015468748","https://openalex.org/W3033529678","https://openalex.org/W3034561418","https://openalex.org/W3034573343","https://openalex.org/W3034850762","https://openalex.org/W3039017601","https://openalex.org/W3045733172","https://openalex.org/W3091156754","https://openalex.org/W3103682594","https://openalex.org/W3105478763","https://openalex.org/W3119293022","https://openalex.org/W3123615524","https://openalex.org/W3155888652","https://openalex.org/W3161820423","https://openalex.org/W3166148088","https://openalex.org/W3170490008","https://openalex.org/W3173529047","https://openalex.org/W3200409031","https://openalex.org/W4287888039","https://openalex.org/W4309087688","https://openalex.org/W4353089798","https://openalex.org/W4385573804"],"related_works":["https://openalex.org/W4389156824","https://openalex.org/W4389520033","https://openalex.org/W3103682594","https://openalex.org/W4226218991","https://openalex.org/W3212731309","https://openalex.org/W4393160271","https://openalex.org/W4383535610","https://openalex.org/W7020486239","https://openalex.org/W3093260394","https://openalex.org/W4394673039"],"abstract_inverted_index":{"Transformer":[0,21,54],"models":[1,34,55],"cannot":[2],"easily":[3],"scale":[4],"to":[5,9,20,24,66,75,87,91,125],"long":[6],"sequences":[7],"due":[8],"their":[10,39,78],"O(N":[11],"2":[12],")":[13],"time":[14],"and":[15,31,61,72,111,128],"space":[16],"complexity.This":[17],"has":[18,45,106],"led":[19],"variants":[22,52],"seeking":[23],"lower":[25],"computational":[26],"complexity,":[27],"such":[28,33,121],"as":[29,122],"Longformer":[30],"Performer.While":[32],"have":[35],"theoretically":[36],"greater":[37],"efficiency,":[38],"effectiveness":[40],"on":[41,56,77,108],"real":[42],"NLP":[43,59],"tasks":[44,60],"not":[46],"been":[47],"well":[48],"studied.We":[49],"benchmark":[50],"7":[51,62],"of":[53,70],"5":[57],"difficult":[58],"datasets.We":[63],"design":[64],"experiments":[65],"isolate":[67],"the":[68,100],"effect":[69],"pretraining":[71],"hyperparameter":[73],"settings,":[74],"focus":[76],"capacity":[79],"for":[80],"long-range":[81,104],"attention.Moreover,":[82],"we":[83],"present":[84],"various":[85],"methods":[86],"investigate":[88],"attention":[89,102,124],"behaviors":[90],"illuminate":[92],"model":[93],"details":[94],"beyond":[95],"metric":[96],"scores.We":[97],"find":[98],"that":[99],"modified":[101],"in":[103],"transformers":[105],"advantages":[107],"content":[109],"selection":[110],"query-guided":[112],"decoding,":[113],"but":[114],"they":[115],"come":[116],"with":[117],"previously":[118],"unrecognized":[119],"drawbacks":[120],"insufficient":[123],"distant":[126],"tokens":[127],"accumulated":[129],"approximation":[130],"error.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-09-10T00:00:00"}