{"id":"https://openalex.org/W4389520146","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.370","title":"Adapting Pretrained Text-to-Text Models for Long Text Sequences","display_name":"Adapting Pretrained Text-to-Text Models for Long Text Sequences","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389520146","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.370"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.370","pdf_url":"https://aclanthology.org/2023.findings-emnlp.370.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.370.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110635444","display_name":"Wenhan Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenhan Xiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081592288","display_name":"Anchit Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anchit Gupta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073890145","display_name":"Shubham Toshniwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubham Toshniwal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067997502","display_name":"Yashar Mehdad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashar Mehdad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027596907","display_name":"Scott Yih","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Yih","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110635444"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6224,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91970537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9872999787330627,"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":0.8717612624168396},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7828789949417114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6535340547561646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6370206475257874},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6334695816040039},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5695276856422424},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5188575983047485},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5138416886329651},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5131335854530334},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.4683645963668823},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.44815951585769653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4223138391971588},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4110347032546997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33246681094169617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717612624168396},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7828789949417114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6535340547561646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6370206475257874},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6334695816040039},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5695276856422424},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5188575983047485},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5138416886329651},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5131335854530334},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.4683645963668823},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44815951585769653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4223138391971588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4110347032546997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33246681094169617},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.370","pdf_url":"https://aclanthology.org/2023.findings-emnlp.370.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.370","pdf_url":"https://aclanthology.org/2023.findings-emnlp.370.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389520146.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2578338321","https://openalex.org/W2805206884","https://openalex.org/W2923014074","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2963926728","https://openalex.org/W2963963993","https://openalex.org/W2971034336","https://openalex.org/W2996264288","https://openalex.org/W3015468748","https://openalex.org/W3033529678","https://openalex.org/W3034999214","https://openalex.org/W3105238007","https://openalex.org/W3118781290","https://openalex.org/W3123615524","https://openalex.org/W3131922516","https://openalex.org/W3153603860","https://openalex.org/W3156789018","https://openalex.org/W3159259047","https://openalex.org/W3161820423","https://openalex.org/W3163073193","https://openalex.org/W3169942382","https://openalex.org/W3170490008","https://openalex.org/W3171639395","https://openalex.org/W3207546842","https://openalex.org/W3209374680","https://openalex.org/W4225644300","https://openalex.org/W4225727438","https://openalex.org/W4225958595","https://openalex.org/W4286750685","https://openalex.org/W4287183331","https://openalex.org/W4287323699","https://openalex.org/W4287667694","https://openalex.org/W4287692509","https://openalex.org/W4287704453","https://openalex.org/W4287824654","https://openalex.org/W4287888039","https://openalex.org/W4288089799","https://openalex.org/W4295838474","https://openalex.org/W4299567010","https://openalex.org/W4306672396","https://openalex.org/W4309793872","https://openalex.org/W4321340837","https://openalex.org/W4385245566","https://openalex.org/W4385573804","https://openalex.org/W4385573994","https://openalex.org/W4386566496","https://openalex.org/W4389518794"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3010337296","https://openalex.org/W4206715480","https://openalex.org/W2988673764","https://openalex.org/W2996388263","https://openalex.org/W4385890381","https://openalex.org/W2402231715","https://openalex.org/W2986367395","https://openalex.org/W4388685619"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,7,36],"empirical":[3],"study":[4,18],"of":[5,22,70,75,130],"adapting":[6],"existing":[8,44,97],"pretrained":[9],"text-to-text":[10],"model":[11,27,62,116,144],"for":[12],"long-sequence":[13],"inputs.":[14],"Through":[15],"a":[16,64,87,114],"comprehensive":[17],"along":[19],"three":[20],"axes":[21],"the":[23,50,61,76,127,131],"pretraining":[24,32,77],"pipeline":[25],"\u2013":[26],"architecture,":[28],"optimization":[29],"objective,":[30],"and":[31,59,125],"corpus,":[33,78],"we":[34,48,79,112],"propose":[35],"effective":[37],"recipe":[38],"to":[39],"build":[40,113],"long-context":[41,115],"models":[42],"from":[43,86],"short-context":[45],"models.":[46],"Specifically,":[47],"replace":[49],"full":[51],"attention":[52],"in":[53,92,105],"transformers":[54],"with":[55,63,68,142],"pooling-augmented":[56],"blockwise":[57],"attention,":[58],"pretrain":[60],"masked-span":[65],"prediction":[66],"task":[67],"spans":[69],"varying":[71],"lengths.":[72],"In":[73],"terms":[74],"find":[80],"that":[81,117],"using":[82,96],"randomly":[83],"concatenated":[84],"short-documents":[85],"large":[88],"open-domain":[89],"corpus":[90],"results":[91],"better":[93],"performance":[94,120],"than":[95],"long":[98],"document":[99],"corpora,":[100],"which":[101],"are":[102],"typically":[103],"limited":[104],"their":[106],"domain":[107],"coverage.":[108],"With":[109],"these":[110],"findings,":[111],"achieves":[118],"competitive":[119],"on":[121,133],"long-text":[122,135],"QA":[123],"tasks":[124],"establishes":[126],"new":[128],"state":[129],"art":[132],"five":[134],"summarization":[136],"datasets,":[137],"often":[138],"outperforming":[139],"previous":[140],"methods":[141],"larger":[143],"sizes.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}