{"id":"https://openalex.org/W2970100546","doi":"https://doi.org/10.18653/v1/d19-1443","title":"Transformer Dissection: An Unified Understanding for Transformer\u2019s Attention via the Lens of Kernel","display_name":"Transformer Dissection: An Unified Understanding for Transformer\u2019s Attention via the Lens of Kernel","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970100546","doi":"https://doi.org/10.18653/v1/d19-1443","mag":"2970100546"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-1443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1443","pdf_url":"https://www.aclweb.org/anthology/D19-1443.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-1443.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015826285","display_name":"Yao-Hung Hubert Tsai","orcid":"https://orcid.org/0000-0001-5312-1875"},"institutions":[{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao-Hung Hubert Tsai","raw_affiliation_strings":["Machine Learning Department,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department,","institution_ids":["https://openalex.org/I4210121368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037832036","display_name":"Shaojie Bai","orcid":"https://orcid.org/0009-0006-7526-5216"},"institutions":[{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojie Bai","raw_affiliation_strings":["Machine Learning Department,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department,","institution_ids":["https://openalex.org/I4210121368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046358579","display_name":"Makoto Yamada","orcid":"https://orcid.org/0000-0001-7508-5094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Makoto Yamada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2010Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Language Technology Institute}, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute}, Carnegie Mellon University","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"institutions":[{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruslan Salakhutdinov","raw_affiliation_strings":["Machine Learning Department,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department,","institution_ids":["https://openalex.org/I4210121368"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3121,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86092626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4343","last_page":"4352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/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":0.9968000054359436,"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/transformer","display_name":"Transformer","score":0.7817277312278748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7144243717193604},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6071944236755371},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5313642024993896},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4979863166809082},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4854021966457367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47305741906166077},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.4212651252746582},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24005413055419922},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14027753472328186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11248922348022461},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10178813338279724},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09018167853355408},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0890859067440033}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7817277312278748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144243717193604},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6071944236755371},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5313642024993896},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4979863166809082},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4854021966457367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47305741906166077},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4212651252746582},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24005413055419922},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14027753472328186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11248922348022461},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10178813338279724},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09018167853355408},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0890859067440033},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-1443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1443","pdf_url":"https://www.aclweb.org/anthology/D19-1443.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.11775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.11775","pdf_url":"https://arxiv.org/pdf/1908.11775","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,"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:2970100546","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.11775v4","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,"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.1908.11775","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.11775","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-1443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1443","pdf_url":"https://www.aclweb.org/anthology/D19-1443.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2570099219","display_name":"NCS-FO:Collaborative Research:Decoding and Reconstructing the Neural Basis of Real World Social Perception","funder_award_id":"1734868","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3550935145","display_name":null,"funder_award_id":"N000141812861","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G574185058","display_name":"SCH: INT: Collaborative Research: Dyadic Behavior Informatics for Psychotherapy Process and Outcome","funder_award_id":"1722822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970100546.pdf","grobid_xml":"https://content.openalex.org/works/W2970100546.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1560724230","https://openalex.org/W1571975558","https://openalex.org/W2090923791","https://openalex.org/W2097073572","https://openalex.org/W2130942839","https://openalex.org/W2151416941","https://openalex.org/W2525332836","https://openalex.org/W2789541106","https://openalex.org/W2792764867","https://openalex.org/W2891815651","https://openalex.org/W2894384847","https://openalex.org/W2896457183","https://openalex.org/W2908802752","https://openalex.org/W2911109671","https://openalex.org/W2933138175","https://openalex.org/W2940744433","https://openalex.org/W2962892300","https://openalex.org/W2963091558","https://openalex.org/W2963403868","https://openalex.org/W2964051877","https://openalex.org/W2964135722","https://openalex.org/W2964190861","https://openalex.org/W2982515679","https://openalex.org/W3038029863"],"related_works":["https://openalex.org/W2983902802","https://openalex.org/W3175217541","https://openalex.org/W2952902402","https://openalex.org/W3200784729","https://openalex.org/W2997753998","https://openalex.org/W3047109227","https://openalex.org/W2964308564","https://openalex.org/W2963403868","https://openalex.org/W2194775991","https://openalex.org/W3099811568","https://openalex.org/W2894384847","https://openalex.org/W3038029863","https://openalex.org/W2996657533","https://openalex.org/W3149251347","https://openalex.org/W2770392859","https://openalex.org/W84155667","https://openalex.org/W3192611602","https://openalex.org/W2554460311","https://openalex.org/W2926076923","https://openalex.org/W2770868259"],"abstract_inverted_index":{"Yao-Hung":[0],"Hubert":[1],"Tsai,":[2],"Shaojie":[3],"Bai,":[4],"Makoto":[5],"Yamada,":[6],"Louis-Philippe":[7],"Morency,":[8],"Ruslan":[9],"Salakhutdinov.":[10],"Proceedings":[11],"of":[12],"the":[13,24],"2019":[14],"Conference":[15,28],"on":[16,29],"Empirical":[17],"Methods":[18],"in":[19],"Natural":[20,30],"Language":[21,31],"Processing":[22,32],"and":[23],"9th":[25],"International":[26],"Joint":[27],"(EMNLP-IJCNLP).":[33],"2019.":[34]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}