{"id":"https://openalex.org/W3140329232","doi":"https://doi.org/10.1145/3445815.3445856","title":"Using Triangle Exchange Mechanism to Accelerate the Pre-training Convergence Speed of BERT","display_name":"Using Triangle Exchange Mechanism to Accelerate the Pre-training Convergence Speed of BERT","publication_year":2020,"publication_date":"2020-12-11","ids":{"openalex":"https://openalex.org/W3140329232","doi":"https://doi.org/10.1145/3445815.3445856","mag":"3140329232"},"language":"en","primary_location":{"id":"doi:10.1145/3445815.3445856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445815.3445856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 4th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008743173","display_name":"Jingjing Liao","orcid":"https://orcid.org/0009-0007-4684-7564"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Liao","raw_affiliation_strings":["College of Computer & Information Science Southwest University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer & Information Science Southwest University, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039482617","display_name":"Nanzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanzhi Wang","raw_affiliation_strings":["College of Computer & Information Science Southwest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer & Information Science Southwest University","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102228100","display_name":"Guocai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocai Yang","raw_affiliation_strings":["College of Computer & Information Science Southwest University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer & Information Science Southwest University, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"254","last_page":"260"},"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":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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/security-token","display_name":"Security token","score":0.8716496229171753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870957851409912},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7356071472167969},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6603749394416809},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6265147924423218},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6078620553016663},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.598222553730011},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5762872099876404},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.552348256111145},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5280462503433228},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4741900861263275},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46670863032341003},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.440228134393692},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.42171043157577515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40475812554359436},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3642246425151825},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08895254135131836},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.08493700623512268},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06981033086776733}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8716496229171753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870957851409912},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7356071472167969},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6603749394416809},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6265147924423218},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6078620553016663},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.598222553730011},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5762872099876404},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.552348256111145},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5280462503433228},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4741900861263275},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46670863032341003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.440228134393692},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.42171043157577515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40475812554359436},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3642246425151825},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08895254135131836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.08493700623512268},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06981033086776733},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3445815.3445856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445815.3445856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 4th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1981276685","https://openalex.org/W2120615054","https://openalex.org/W2171928131","https://openalex.org/W2914120296","https://openalex.org/W2950577311","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963807318","https://openalex.org/W2970119519","https://openalex.org/W2970597249","https://openalex.org/W2978017171","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W6679436768","https://openalex.org/W6680532216","https://openalex.org/W6685158001","https://openalex.org/W6739901393","https://openalex.org/W6763240421"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"As":[0],"a":[1,63,120],"current-leading":[2],"language":[3],"representation":[4],"model,":[5,144],"BERT":[6,35],"is":[7],"entirely":[8],"constructed":[9],"by":[10,101],"self-attention.":[11],"The":[12,80],"special":[13,102],"weighted":[14],"sum":[15],"method":[16,81],"of":[17,30,59,86,104,112,140],"the":[18,23,28,56,70,83,109,113,132,137,141,150],"self-attention":[19,105,133],"mechanism":[20],"can":[21,127],"capture":[22],"longer-term":[24],"dependency,":[25],"meanwhile":[26],"unable":[27],"modeling":[29,54,77],"timing":[31],"sequence":[32],"information":[33],"structurally.":[34],"added":[36],"position":[37],"embedding":[38],"to":[39,51,74,89,95,131],"alleviate":[40],"this":[41,47],"problem,":[42],"but":[43],"we":[44],"noticed":[45],"that":[46,125],"would":[48],"also":[49],"lead":[50],"inaccurate":[52],"context":[53,76],"in":[55],"early":[57],"stage":[58],"training.":[60],"We":[61],"propose":[62],"novel":[64],"approach,":[65],"Triangle":[66],"Exchange":[67],"(TE),":[68],"optimizing":[69],"model":[71],"internal":[72],"structure":[73],"make":[75],"more":[78],"accurate.":[79],"enables":[82],"attention":[84,117],"values":[85,118],"each":[87],"token":[88],"its":[90],"above":[91],"and":[92,145],"below":[93],"tokens":[94],"be":[96,128],"calculated":[97],"from":[98],"different":[99],"heads":[100],"disposing":[103],"matrices,":[106],"thus":[107],"expanding":[108],"variable":[110],"range":[111],"difference":[114],"be-tween":[115],"contextual":[116],"for":[119],"given":[121],"token.":[122],"Experiments":[123],"show":[124],"TE":[126],"flexibly":[129],"applied":[130],"mechanism,":[134],"significantly":[135],"improves":[136],"convergence":[138],"speed":[139],"masked":[142],"LM":[143],"obtains":[146],"higher":[147],"accuracy":[148],"on":[149],"pre-training":[151],"procedures":[152],"compared":[153],"with":[154],"BERT.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}