{"id":"https://openalex.org/W2977313660","doi":"https://doi.org/10.18653/v1/d19-5624","title":"Interrogating the Explanatory Power of Attention in Neural Machine Translation","display_name":"Interrogating the Explanatory Power of Attention in Neural Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2977313660","doi":"https://doi.org/10.18653/v1/d19-5624","mag":"2977313660"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5624","pdf_url":"https://www.aclweb.org/anthology/D19-5624.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 3rd Workshop on Neural Generation and Translation","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/D19-5624.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026225187","display_name":"Pooya Moradi","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Pooya Moradi","raw_affiliation_strings":["University 8888 University Drive Burnaby, BC, Canada","University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University 8888 University Drive Burnaby, BC, Canada","institution_ids":[]},{"raw_affiliation_string":"University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017685924","display_name":"Nishant Kambhatla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishant Kambhatla","raw_affiliation_strings":["University 8888 University Drive Burnaby, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University 8888 University Drive Burnaby, BC, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081354508","display_name":"Anoop Sarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anoop Sarkar","raw_affiliation_strings":["University 8888 University Drive Burnaby, BC, Canada","[Simon Fraser University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University 8888 University Drive Burnaby, BC, Canada","institution_ids":[]},{"raw_affiliation_string":"[Simon Fraser University]","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58754929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.996999979019165,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9370810985565186},{"id":"https://openalex.org/keywords/explanatory-power","display_name":"Explanatory power","score":0.824690580368042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638641357421875},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6485739350318909},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6029384136199951},{"id":"https://openalex.org/keywords/explanatory-model","display_name":"Explanatory model","score":0.5653073787689209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5396367311477661},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5246363282203674},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4642442464828491},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.46177637577056885},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.43236178159713745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3933577239513397},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.364888072013855},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3623315095901489},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29962587356567383},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18565332889556885},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12243589758872986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09476688504219055}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9370810985565186},{"id":"https://openalex.org/C2777402642","wikidata":"https://www.wikidata.org/wiki/Q2557224","display_name":"Explanatory power","level":2,"score":0.824690580368042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638641357421875},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6485739350318909},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6029384136199951},{"id":"https://openalex.org/C2778638050","wikidata":"https://www.wikidata.org/wiki/Q5421252","display_name":"Explanatory model","level":2,"score":0.5653073787689209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396367311477661},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5246363282203674},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4642442464828491},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.46177637577056885},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.43236178159713745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3933577239513397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.364888072013855},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3623315095901489},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29962587356567383},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18565332889556885},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12243589758872986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09476688504219055},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-5624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5624","pdf_url":"https://www.aclweb.org/anthology/D19-5624.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 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.00139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.00139","pdf_url":"https://arxiv.org/pdf/1910.00139","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:2977313660","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.00139v1","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.1910.00139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.00139","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/d19-5624","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5624","pdf_url":"https://www.aclweb.org/anthology/D19-5624.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 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G2980479518","display_name":null,"funder_award_id":"RGPIN-2018","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320330045","display_name":"Minist\u00e8re de la D\u00e9fense Nationale","ror":"https://ror.org/035rreb34"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2977313660.pdf","grobid_xml":"https://content.openalex.org/works/W2977313660.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1902237438","https://openalex.org/W1951216520","https://openalex.org/W1971453323","https://openalex.org/W2130942839","https://openalex.org/W2195388612","https://openalex.org/W2292919134","https://openalex.org/W2561386235","https://openalex.org/W2562979205","https://openalex.org/W2741040846","https://openalex.org/W2752194699","https://openalex.org/W2885396331","https://openalex.org/W2897507397","https://openalex.org/W2934842096","https://openalex.org/W2950228383","https://openalex.org/W2950635152","https://openalex.org/W2953483091","https://openalex.org/W2962816513","https://openalex.org/W2962843949","https://openalex.org/W2962851944","https://openalex.org/W2962886257","https://openalex.org/W2963123635","https://openalex.org/W2963212250","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2963549191","https://openalex.org/W2964045325","https://openalex.org/W2964159778","https://openalex.org/W2964165364","https://openalex.org/W2964174820","https://openalex.org/W2964178496","https://openalex.org/W2964298349","https://openalex.org/W2964308564","https://openalex.org/W2971296520","https://openalex.org/W2972324944","https://openalex.org/W2972498556"],"related_works":["https://openalex.org/W2973291083","https://openalex.org/W2934842096","https://openalex.org/W2968210605","https://openalex.org/W3003410553","https://openalex.org/W3202973005","https://openalex.org/W3126483755","https://openalex.org/W3092292656","https://openalex.org/W3156102243","https://openalex.org/W2151234430","https://openalex.org/W3093914553","https://openalex.org/W3114476669","https://openalex.org/W2972075500","https://openalex.org/W2965046886","https://openalex.org/W2111500549","https://openalex.org/W2895118614","https://openalex.org/W3211640232","https://openalex.org/W2189604337","https://openalex.org/W3201964789","https://openalex.org/W3163611453","https://openalex.org/W438769618"],"abstract_inverted_index":{"Attention":[0],"models":[1,71,118,138],"have":[2],"become":[3],"a":[4,26,42,108,148],"crucial":[5,74],"component":[6],"in":[7,24,47,102,129],"neural":[8],"machine":[9],"translation":[10,104],"(NMT).":[11],"They":[12],"are":[13],"often":[14],"implicitly":[15],"or":[16],"explicitly":[17],"used":[18],"to":[19,37,90,107],"justify":[20],"the":[21,51,60,64,77,88,95,103,111,144],"model's":[22],"decision":[23],"generating":[25],"specific":[27],"token":[28],"but":[29,67],"it":[30],"has":[31],"not":[32],"yet":[33],"been":[34],"rigorously":[35],"established":[36],"what":[38],"extent":[39,89],"attention":[40,55,70,79,84,113,117,137],"is":[41],"reliable":[43],"source":[44],"of":[45,54,62,76,97,110,121,126],"information":[46],"NMT.":[48],"To":[49],"evaluate":[50],"explanatory":[52],"power":[53],"for":[56],"NMT,":[57],"we":[58,86],"examine":[59],"possibility":[61],"yielding":[63],"same":[65],"prediction":[66],"with":[68],"counterfactual":[69,83,116],"that":[72,136],"modify":[73],"aspects":[75],"trained":[78],"model.":[80,150],"Using":[81],"these":[82],"mechanisms":[85],"assess":[87],"which":[91],"they":[92],"still":[93],"preserve":[94],"generation":[96],"function":[98,122],"and":[99,124],"content":[100,127],"words":[101,123,128],"process.":[105],"Compared":[106],"state":[109],"art":[112],"model,":[114],"our":[115,130],"produce":[119],"68%":[120],"21%":[125],"German-English":[131],"dataset.":[132],"Our":[133],"experiments":[134],"demonstrate":[135],"by":[139,147],"themselves":[140],"cannot":[141],"reliably":[142],"explain":[143],"decisions":[145],"made":[146],"NMT":[149],"1":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}