{"id":"https://openalex.org/W2949202705","doi":"https://doi.org/10.18653/v1/p19-3007","title":"A Multiscale Visualization of Attention in the Transformer Model","display_name":"A Multiscale Visualization of Attention in the Transformer Model","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949202705","doi":"https://doi.org/10.18653/v1/p19-3007","mag":"2949202705"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-3007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3007","pdf_url":"https://www.aclweb.org/anthology/P19-3007.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","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/P19-3007.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044735229","display_name":"Jesse Vig","orcid":null},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jesse Vig","raw_affiliation_strings":["Palo Alto Research Center 3333 Coyote Hill Road Palo Alto, CA 94304"],"affiliations":[{"raw_affiliation_string":"Palo Alto Research Center 3333 Coyote Hill Road Palo Alto, CA 94304","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044735229"],"corresponding_institution_ids":["https://openalex.org/I173498003"],"apc_list":null,"apc_paid":null,"fwci":8.6797,"has_fulltext":true,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98107991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9959999918937683,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9959999918937683,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10028","display_name":"Topic Modeling","score":0.9807999730110168,"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/transformer","display_name":"Transformer","score":0.8011891841888428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673357129096985},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6320752501487732},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.6152623891830444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48891082406044006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35483184456825256},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11706987023353577}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8011891841888428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673357129096985},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6320752501487732},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.6152623891830444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48891082406044006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35483184456825256},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11706987023353577},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-3007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3007","pdf_url":"https://www.aclweb.org/anthology/P19-3007.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.05714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.05714","pdf_url":"https://arxiv.org/pdf/1906.05714","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":null,"raw_type":"text"},{"id":"mag:2949202705","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1906.05714","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.1906.05714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.05714","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/p19-3007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3007","pdf_url":"https://www.aclweb.org/anthology/P19-3007.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949202705.pdf","grobid_xml":"https://content.openalex.org/works/W2949202705.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2118463056","https://openalex.org/W2610881169","https://openalex.org/W2626778328","https://openalex.org/W2760327630","https://openalex.org/W2799118206","https://openalex.org/W2890353432","https://openalex.org/W2906152891","https://openalex.org/W2934842096","https://openalex.org/W2951528897","https://openalex.org/W2962958286","https://openalex.org/W2962965405","https://openalex.org/W2963341956","https://openalex.org/W2963418779","https://openalex.org/W2963503967","https://openalex.org/W2963526187","https://openalex.org/W2964308564","https://openalex.org/W2972498556","https://openalex.org/W3128232076"],"related_works":["https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2064675550","https://openalex.org/W2972324944","https://openalex.org/W2787560479","https://openalex.org/W2250539671","https://openalex.org/W2963310665","https://openalex.org/W3030163527","https://openalex.org/W2970597249","https://openalex.org/W2969624041","https://openalex.org/W2525778437","https://openalex.org/W3015468748","https://openalex.org/W2996428491","https://openalex.org/W2964121744","https://openalex.org/W2950577311","https://openalex.org/W2940744433","https://openalex.org/W2752194699","https://openalex.org/W3127742036","https://openalex.org/W2971594074"],"abstract_inverted_index":{"The":[0],"Transformer":[1,55],"is":[2,26],"a":[3,14,34,83],"sequence":[4],"model":[5,35,40,56,65,106,116],"that":[6,27,73],"forgoes":[7],"traditional":[8],"recurrent":[9],"architectures":[10],"in":[11,53],"favor":[12],"of":[13,23,80],"fully":[15],"attention-based":[16],"approach.":[17],"Besides":[18],"improving":[19],"performance,":[20],"an":[21,70],"advantage":[22],"using":[24],"attention":[25,51,75,88,110],"it":[28],"can":[29,57],"also":[30],"help":[31],"to":[32,43,60,115],"interpret":[33],"by":[36],"showing":[37],"how":[38],"the":[39,48,54,64,87,92],"assigns":[41],"weight":[42],"different":[44],"input":[45],"elements.":[46],"However,":[47],"multi-layer,":[49],"multi-head":[50],"mechanism":[52],"be":[58],"difficult":[59],"decipher.":[61],"To":[62],"make":[63],"more":[66],"accessible,":[67],"we":[68],"introduce":[69],"open-source":[71],"tool":[72,93],"visualizes":[74],"at":[76],"multiple":[77],"scales,":[78],"each":[79],"which":[81],"provides":[82],"unique":[84],"perspective":[85],"on":[86,94],"mechanism.":[89],"We":[90],"demonstrate":[91],"BERT":[95],"and":[96,99,112],"OpenAI":[97],"GPT-2":[98],"present":[100],"three":[101],"example":[102],"use":[103],"cases:":[104],"detecting":[105],"bias,":[107],"locating":[108],"relevant":[109],"heads,":[111],"linking":[113],"neurons":[114],"behavior.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}