{"id":"https://openalex.org/W4385573392","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.756","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","display_name":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385573392","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.756"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.756","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.756","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-main.756","pdf_url":"https://aclanthology.org/2022.emnlp-main.756.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2022 Conference on Empirical Methods in Natural Language Processing","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/2022.emnlp-main.756.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004217423","display_name":"Neeraj Varshney","orcid":"https://orcid.org/0000-0003-0752-2103","observed_orcids":["https://orcid.org/0000-0003-0752-2103"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraj Varshney","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta R. Baral","orcid":"https://orcid.org/0000-0002-7549-723X","observed_orcids":["https://orcid.org/0000-0002-7549-723X"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":2.6191,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.92328077,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11007","last_page":"11021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5737000107765198,"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":0.5737000107765198,"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":0.2863999903202057,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11509999632835388,"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/computational-efficiency","display_name":"computational efficiency","score":0.6259999871253967},{"id":"https://openalex.org/keywords/prediction-accuracy","display_name":"prediction accuracy","score":0.7710000276565552},{"id":"https://openalex.org/keywords/model-capacity","display_name":"model capacity","score":0.5099999904632568},{"id":"https://openalex.org/keywords/inference-cost-reduction","display_name":"inference cost reduction","score":0.609000027179718},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204718232154846},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6807515621185303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.571998655796051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5654529333114624},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5622255802154541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594176650047302},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5228871703147888},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.452923446893692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32389408349990845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20761200785636902},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.756","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.756","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-main.756","pdf_url":"https://aclanthology.org/2022.emnlp-main.756.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.05528","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05528","pdf_url":"https://arxiv.org/pdf/2210.05528","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.2210.05528","doi":"https://doi.org/10.48550/arxiv.2210.05528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.05528","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.756","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.756","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-main.756","pdf_url":"https://aclanthology.org/2022.emnlp-main.756.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385573392.pdf","grobid_xml":"https://content.openalex.org/works/W4385573392.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1840435438","https://openalex.org/W2251939518","https://openalex.org/W2531327146","https://openalex.org/W2607892599","https://openalex.org/W2806120502","https://openalex.org/W2913946806","https://openalex.org/W2923014074","https://openalex.org/W2932893307","https://openalex.org/W2952603081","https://openalex.org/W2962989446","https://openalex.org/W2963341956","https://openalex.org/W2963430447","https://openalex.org/W2963995027","https://openalex.org/W2965373594","https://openalex.org/W2979691890","https://openalex.org/W2981852735","https://openalex.org/W2990704537","https://openalex.org/W2996035354","https://openalex.org/W2997006708","https://openalex.org/W2998183051","https://openalex.org/W3002104146","https://openalex.org/W3022719076","https://openalex.org/W3026404337","https://openalex.org/W3034408878","https://openalex.org/W3034742519","https://openalex.org/W3035038672","https://openalex.org/W3044749682","https://openalex.org/W3098576111","https://openalex.org/W3101367735","https://openalex.org/W3101731278","https://openalex.org/W3104537233","https://openalex.org/W3105966348","https://openalex.org/W3174702398","https://openalex.org/W3174708387","https://openalex.org/W3174770825","https://openalex.org/W3175987672","https://openalex.org/W3176828726","https://openalex.org/W3177468934","https://openalex.org/W3196295870","https://openalex.org/W3201090304","https://openalex.org/W3207118113","https://openalex.org/W4221138792","https://openalex.org/W4221146568","https://openalex.org/W4226087293","https://openalex.org/W4285111874","https://openalex.org/W4285298351","https://openalex.org/W4286324953"],"related_works":["https://openalex.org/W4399354026","https://openalex.org/W4400374380","https://openalex.org/W2788178548","https://openalex.org/W4281552875","https://openalex.org/W4224075666","https://openalex.org/W4392224111","https://openalex.org/W3110515436","https://openalex.org/W6957687027","https://openalex.org/W4399198692","https://openalex.org/W4394907048"],"abstract_inverted_index":{"Do":[0],"all":[1],"instances":[2,15],"need":[3],"inference":[4],"through":[5],"the":[6,32,74,89,93,122,129,137],"big":[7],"models":[8,55,77,127],"for":[9,30,79],"a":[10,47,52],"correct":[11],"prediction?Perhaps":[12],"not;":[13],"some":[14],"are":[16],"easy":[17],"and":[18,92,107,131],"can":[19],"be":[20],"answered":[21],"correctly":[22],"by":[23],"even":[24],"small":[25],"capacity":[26],"models.This":[27],"provides":[28],"opportunities":[29],"improving":[31],"computational":[33,90],"efficiency":[34,91,138],"of":[35,54,56,76,116,124,148],"systems.In":[36],"this":[37],"work,":[38],"we":[39,83,140],"present":[40],"an":[41,114],"explorative":[42],"study":[43,121],"on":[44],"'model":[45],"cascading',":[46],"simple":[48],"technique":[49],"that":[50,71,85,133,142],"utilizes":[51],"collection":[53],"varying":[57],"capacities":[58],"to":[59,103,118],"accurately":[60],"yet":[61],"efficiently":[62],"output":[63],"predictions.Through":[64],"comprehensive":[65],"experiments":[66],"in":[67,73,97,128,156],"multiple":[68],"task":[69],"settings":[70],"differ":[72],"number":[75],"available":[78],"cascading":[80,86,100],"(K":[81],"value),":[82],"show":[84,132],"improves":[87],"both":[88],"prediction":[94,111],"accuracy.For":[95],"instance,":[96],"K=3":[98],"setting,":[99],"saves":[101],"up":[102,117],"88.93%":[104],"computation":[105],"cost":[106],"consistently":[108],"achieves":[109],"superior":[110],"accuracy":[112],"with":[113],"improvement":[115],"2.18%.We":[119],"also":[120],"impact":[123],"introducing":[125],"additional":[126],"cascade":[130],"it":[134],"further":[135],"increases":[136],"improvements.Finally,":[139],"hope":[141],"our":[143],"work":[144],"will":[145],"facilitate":[146],"development":[147],"efficient":[149],"NLP":[150],"systems":[151],"making":[152],"their":[153],"widespread":[154],"adoption":[155],"real-world":[157],"applications":[158],"possible.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2023-08-05T00:00:00"}