{"id":"https://openalex.org/W2890177507","doi":"https://doi.org/10.18653/v1/d18-1477","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","display_name":"Simple Recurrent Units for Highly Parallelizable Recurrence","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890177507","doi":"https://doi.org/10.18653/v1/d18-1477","mag":"2890177507"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1477","pdf_url":"https://www.aclweb.org/anthology/D18-1477.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":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1477.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030752617","display_name":"Tao Le\u00ed","orcid":"https://orcid.org/0000-0002-0900-1582"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Lei","raw_affiliation_strings":["ASAPP Inc","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707101","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-2842-6340"},"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google Brain","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084195779","display_name":"Sida I. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sida I. Wang","raw_affiliation_strings":["ASAPP Inc","Princeton University","Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112473700","display_name":"Hui Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Dai","raw_affiliation_strings":["ASAPP Inc","University of Chicago, Chicago, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"University of Chicago, Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047026141","display_name":"Yoav Artzi","orcid":"https://orcid.org/0000-0002-4605-6144"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoav Artzi","raw_affiliation_strings":["ASAPP Inc","Cornell University","Cornell University, Ithaca, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5893,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.9730782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4470","last_page":"4481"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.9114114046096802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8284581899642944},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7755346298217773},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6818769574165344},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5543003678321838},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5436974167823792},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5323774218559265},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5213209986686707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5201621055603027},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45626071095466614},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.430071622133255},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.413699209690094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1973446011543274},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13918066024780273},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12889808416366577}],"concepts":[{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.9114114046096802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284581899642944},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7755346298217773},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6818769574165344},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5543003678321838},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5436974167823792},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5323774218559265},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5213209986686707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5201621055603027},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45626071095466614},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.430071622133255},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.413699209690094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1973446011543274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13918066024780273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12889808416366577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1477","pdf_url":"https://www.aclweb.org/anthology/D18-1477.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":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1709.02755","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.02755","pdf_url":"https://arxiv.org/pdf/1709.02755","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2890177507","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1709.02755.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1709.02755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1709.02755","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1477","pdf_url":"https://www.aclweb.org/anthology/D18-1477.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":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890177507.pdf","grobid_xml":"https://content.openalex.org/works/W2890177507.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1591801644","https://openalex.org/W1600744878","https://openalex.org/W1603614877","https://openalex.org/W1677182931","https://openalex.org/W1689711448","https://openalex.org/W1872348600","https://openalex.org/W1876691451","https://openalex.org/W1902237438","https://openalex.org/W1938755728","https://openalex.org/W2057653135","https://openalex.org/W2064675550","https://openalex.org/W2100664567","https://openalex.org/W2106429429","https://openalex.org/W2113131493","https://openalex.org/W2114524997","https://openalex.org/W2144012961","https://openalex.org/W2160306971","https://openalex.org/W2160660844","https://openalex.org/W2166637769","https://openalex.org/W2181607856","https://openalex.org/W2194775991","https://openalex.org/W2221366174","https://openalex.org/W2251939518","https://openalex.org/W2293634267","https://openalex.org/W2342173569","https://openalex.org/W2396384435","https://openalex.org/W2403195671","https://openalex.org/W2427527485","https://openalex.org/W2474388053","https://openalex.org/W2510842514","https://openalex.org/W2525778437","https://openalex.org/W2531443350","https://openalex.org/W2549416390","https://openalex.org/W2553303224","https://openalex.org/W2605203995","https://openalex.org/W2611884151","https://openalex.org/W2613904329","https://openalex.org/W2618101654","https://openalex.org/W2618854269","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2740747242","https://openalex.org/W2740765036","https://openalex.org/W2792376130","https://openalex.org/W2796979813","https://openalex.org/W2949300694","https://openalex.org/W2950297649","https://openalex.org/W2950621961","https://openalex.org/W2950910987","https://openalex.org/W2951060897","https://openalex.org/W2951815760","https://openalex.org/W2952186591","https://openalex.org/W2952339051","https://openalex.org/W2952436057","https://openalex.org/W2962905474","https://openalex.org/W2962939986","https://openalex.org/W2962985038","https://openalex.org/W2963079395","https://openalex.org/W2963212250","https://openalex.org/W2963266340","https://openalex.org/W2963323889","https://openalex.org/W2963347649","https://openalex.org/W2963706817","https://openalex.org/W2963748792","https://openalex.org/W2963918774","https://openalex.org/W2963970792","https://openalex.org/W2963983719","https://openalex.org/W2964081539","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2064675550","https://openalex.org/W2964308564","https://openalex.org/W2626778328","https://openalex.org/W2751185861","https://openalex.org/W2194775991","https://openalex.org/W1522301498","https://openalex.org/W2952436057","https://openalex.org/W2950635152","https://openalex.org/W2250539671","https://openalex.org/W2949888546","https://openalex.org/W2095705004","https://openalex.org/W1924770834","https://openalex.org/W2251939518","https://openalex.org/W2613904329","https://openalex.org/W2540404261","https://openalex.org/W2525778437","https://openalex.org/W2120615054","https://openalex.org/W2112796928","https://openalex.org/W1689711448","https://openalex.org/W1591801644"],"abstract_inverted_index":{"Common":[0],"recurrent":[1,28],"neural":[2],"architectures":[3],"scale":[4],"poorly":[5],"due":[6],"to":[7,39,52],"the":[8,21,60,100],"intrinsic":[9],"difficulty":[10],"in":[11],"parallelizing":[12],"their":[13],"state":[14],"computations.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"propose":[20],"Simple":[22],"Recurrent":[23],"Unit":[24],"(SRU),":[25],"a":[26],"light":[27],"unit":[29],"that":[30],"balances":[31],"model":[32,102],"capacity":[33],"and":[34,47,77,81,87],"scalability.":[35],"SRU":[36,63,68],"is":[37],"designed":[38],"provide":[40],"expressive":[41],"recurrence,":[42],"enable":[43],"highly":[44],"parallelized":[45],"implementation,":[46],"comes":[48],"with":[49],"careful":[50],"initialization":[51],"facilitate":[53],"training":[54],"of":[55,62,95],"deep":[56],"models.":[57,89],"We":[58,90],"demonstrate":[59],"effectiveness":[61],"on":[64,75],"multiple":[65],"NLP":[66],"tasks.":[67],"achieves":[69],"5-9x":[70],"speed-up":[71],"over":[72,99],"cuDNN-optimized":[73],"LSTM":[74,86],"classification":[76],"question":[78],"answering":[79],"datasets,":[80],"delivers":[82],"stronger":[83],"results":[84],"than":[85],"convolutional":[88],"also":[91],"obtain":[92],"an":[93],"average":[94],"0.7":[96],"BLEU":[97],"improvement":[98],"Transformer":[101]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}