{"id":"https://openalex.org/W3030128163","doi":"https://doi.org/10.1109/taslp.2020.2998278","title":"Towards Better Word Alignment in Transformer","display_name":"Towards Better Word Alignment in Transformer","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3030128163","doi":"https://doi.org/10.1109/taslp.2020.2998278","mag":"3030128163"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2998278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998278","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5058104443","display_name":"Kai Song","orcid":"https://orcid.org/0000-0002-1851-3264"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Song","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China","Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049243695","display_name":"Xiaoqing Zhou","orcid":"https://orcid.org/0000-0002-4139-032X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Zhou","raw_affiliation_strings":["Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101462417","display_name":"Heng Yu","orcid":"https://orcid.org/0000-0002-2158-862X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Yu","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113916695","display_name":"Zhongqiang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqiang Huang","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085736941","display_name":"Weihua Luo","orcid":"https://orcid.org/0000-0002-5002-6933"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Luo","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089990864","display_name":"Xiangyu Duan","orcid":"https://orcid.org/0000-0002-7268-8823"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Duan","raw_affiliation_strings":["Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5058104443"],"corresponding_institution_ids":["https://openalex.org/I3923682","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.0605,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81822586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"1801","last_page":"1812"},"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":0.9998000264167786,"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":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7963048219680786},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7389815449714661},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6801971197128296},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.618159294128418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5763112306594849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5743222832679749},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5594468116760254},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5472558736801147},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4970231354236603},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49456116557121277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3926829397678375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09163367748260498},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07550254464149475},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07235264778137207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963048219680786},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7389815449714661},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6801971197128296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.618159294128418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763112306594849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5743222832679749},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5594468116760254},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5472558736801147},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4970231354236603},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49456116557121277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3926829397678375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09163367748260498},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07550254464149475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07235264778137207},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2998278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998278","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G333442003","display_name":null,"funder_award_id":"61673289","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4241254100","display_name":null,"funder_award_id":"61525205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1973923101","https://openalex.org/W2006969979","https://openalex.org/W2101105183","https://openalex.org/W2111798208","https://openalex.org/W2118434577","https://openalex.org/W2133564696","https://openalex.org/W2148708890","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2212703438","https://openalex.org/W2400065810","https://openalex.org/W2437005631","https://openalex.org/W2537667581","https://openalex.org/W2594229957","https://openalex.org/W2606974598","https://openalex.org/W2613904329","https://openalex.org/W2618530766","https://openalex.org/W2757047188","https://openalex.org/W2759932073","https://openalex.org/W2896457183","https://openalex.org/W2903012348","https://openalex.org/W2912070261","https://openalex.org/W2914120296","https://openalex.org/W2933138175","https://openalex.org/W2936627440","https://openalex.org/W2936652946","https://openalex.org/W2946794439","https://openalex.org/W2951770285","https://openalex.org/W2952468927","https://openalex.org/W2952682849","https://openalex.org/W2955347425","https://openalex.org/W2962708992","https://openalex.org/W2962714778","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962834107","https://openalex.org/W2963260202","https://openalex.org/W2963266340","https://openalex.org/W2963341956","https://openalex.org/W2963347649","https://openalex.org/W2963352809","https://openalex.org/W2963403868","https://openalex.org/W2963499882","https://openalex.org/W2963506925","https://openalex.org/W2963598809","https://openalex.org/W2963602293","https://openalex.org/W2963938518","https://openalex.org/W2964029788","https://openalex.org/W2964121744","https://openalex.org/W2964165364","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2964998528","https://openalex.org/W2970045405","https://openalex.org/W2970049541","https://openalex.org/W2970565456","https://openalex.org/W2971296520","https://openalex.org/W4241645538","https://openalex.org/W4288347855","https://openalex.org/W4298393544","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6652311901","https://openalex.org/W6677566513","https://openalex.org/W6679434410","https://openalex.org/W6682026795","https://openalex.org/W6688167117","https://openalex.org/W6726804950","https://openalex.org/W6729202379","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6744707562","https://openalex.org/W6745388339","https://openalex.org/W6755207826","https://openalex.org/W6759081955","https://openalex.org/W6759455113","https://openalex.org/W6761380950","https://openalex.org/W6761889296","https://openalex.org/W6762521896","https://openalex.org/W6762945437","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2463396630","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"While":[0],"neural":[1],"models":[2],"based":[3],"on":[4,66,74,124,151,159,175],"the":[5,9,18,63,103,134,161],"Transformer":[6,73],"architecture":[7],"achieve":[8,169],"State-of-the-Art":[10],"translation":[11,52],"performance,":[12],"it":[13],"is":[14,30],"well":[15,25],"known":[16],"that":[17,133],"learned":[19],"target-to-source":[20],"attentions":[21],"do":[22],"not":[23],"correlate":[24],"with":[26],"word":[27,37,70,97,111,117,163],"alignment.":[28,164],"There":[29],"an":[31],"increasing":[32],"interest":[33],"in":[34,39,46,72,115],"inducing":[35],"accurate":[36],"alignment":[38,71,140,171],"Transformer,":[40],"due":[41],"to":[42,86,106,148],"its":[43],"important":[44],"role":[45],"practical":[47],"applications":[48],"such":[49],"as":[50],"dictionary-guided":[51],"and":[53,61,99],"interactive":[54],"translation.":[55],"In":[56],"this":[57],"article,":[58],"we":[59],"extend":[60],"improve":[62],"recent":[64,157],"work":[65],"unsupervised":[67],"learning":[68,94],"of":[69,90,102,110,128],"two":[75,156],"dimensions:":[76],"a)":[77],"parameter":[78],"initialization":[79],"from":[80],"a":[81],"pre-trained":[82],"cross-lingual":[83],"language":[84,130,153],"model":[85,108],"leverage":[87],"large":[88],"amounts":[89],"monolingual":[91],"data":[92,126],"for":[93],"robust":[95],"contextualized":[96],"representations,":[98],"b)":[100],"regularization":[101],"training":[104],"objective":[105],"directly":[107],"characteristics":[109],"alignments":[112,118],"which":[113],"results":[114,172],"favorable":[116],"receiving":[119],"more":[120],"concentrated":[121],"probabilities.":[122],"Experiments":[123],"benchmark":[125],"sets":[127],"three":[129],"pairs":[131],"show":[132],"proposed":[135],"methods":[136,167],"can":[137,168],"significantly":[138],"reduce":[139],"error":[141],"rate":[142],"(AER)":[143],"by":[144],"at":[145],"least":[146],"3.7":[147],"7.7":[149],"points":[150],"each":[152],"pair":[154],"over":[155],"works":[158],"improving":[160],"Transformer's":[162],"Moreover,":[165],"our":[166],"better":[170],"than":[173],"GIZA++":[174],"certain":[176],"test":[177],"sets.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}