{"id":"https://openalex.org/W4386857706","doi":"https://doi.org/10.1109/taslp.2023.3313445","title":"P-Transformer: Towards Better Document-to-Document Neural Machine Translation","display_name":"P-Transformer: Towards Better Document-to-Document Neural Machine Translation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386857706","doi":"https://doi.org/10.1109/taslp.2023.3313445"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313445","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/A5101701181","display_name":"Yachao Li","orcid":"https://orcid.org/0000-0002-9423-9922"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yachao Li","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369260","display_name":"Junhui Li","orcid":"https://orcid.org/0000-0001-7829-6348"},"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":"Junhui Li","raw_affiliation_strings":["Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042484772","display_name":"Jing Jiang","orcid":"https://orcid.org/0000-0002-5648-2323"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"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":["Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101701181"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":3.1469,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93378533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3859","last_page":"3870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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":0.9643999934196472,"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":0.7725157737731934},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.716505765914917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.669177770614624},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6340559720993042},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6258631348609924},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5539822578430176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031713843345642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44626304507255554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3574991822242737},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12828612327575684},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11256733536720276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08908888697624207}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7725157737731934},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.716505765914917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669177770614624},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6340559720993042},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6258631348609924},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5539822578430176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031713843345642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44626304507255554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3574991822242737},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12828612327575684},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11256733536720276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08908888697624207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313445","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":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8497982794","display_name":null,"funder_award_id":"6203600","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W2184135559","https://openalex.org/W2608029998","https://openalex.org/W2767019613","https://openalex.org/W2799051177","https://openalex.org/W2866343820","https://openalex.org/W2891534142","https://openalex.org/W2896457183","https://openalex.org/W2919624000","https://openalex.org/W2951977278","https://openalex.org/W2952446148","https://openalex.org/W2962712961","https://openalex.org/W2962784628","https://openalex.org/W2962802109","https://openalex.org/W2962943802","https://openalex.org/W2963807318","https://openalex.org/W2963925437","https://openalex.org/W2964093087","https://openalex.org/W2964110616","https://openalex.org/W2964204621","https://openalex.org/W2964289193","https://openalex.org/W2964291396","https://openalex.org/W2970529093","https://openalex.org/W2970550739","https://openalex.org/W2970597249","https://openalex.org/W2970797723","https://openalex.org/W2971278086","https://openalex.org/W2997732209","https://openalex.org/W3001434439","https://openalex.org/W3015468748","https://openalex.org/W3034351728","https://openalex.org/W3034786666","https://openalex.org/W3034999214","https://openalex.org/W3035206215","https://openalex.org/W3035520602","https://openalex.org/W3035629723","https://openalex.org/W3100623455","https://openalex.org/W3101683892","https://openalex.org/W3102507836","https://openalex.org/W3103878009","https://openalex.org/W3105238007","https://openalex.org/W3106210592","https://openalex.org/W3122515622","https://openalex.org/W3166829167","https://openalex.org/W3173680274","https://openalex.org/W3173691187","https://openalex.org/W3186252291","https://openalex.org/W3208527886","https://openalex.org/W3209632425","https://openalex.org/W3211978535","https://openalex.org/W3212781411","https://openalex.org/W3213674000","https://openalex.org/W4205902821","https://openalex.org/W4285121328","https://openalex.org/W4362446075","https://openalex.org/W4385245566","https://openalex.org/W6608792757","https://openalex.org/W6686282164","https://openalex.org/W6736549440","https://openalex.org/W6739901393","https://openalex.org/W6752173134","https://openalex.org/W6753640285","https://openalex.org/W6755207826","https://openalex.org/W6760601182","https://openalex.org/W6763701032","https://openalex.org/W6775034530","https://openalex.org/W6776048684","https://openalex.org/W6779902714","https://openalex.org/W6846377778"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W3098873988","https://openalex.org/W2952599318","https://openalex.org/W2890256614","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Directly":[0],"training":[1,62],"a":[2,73,110,151,169,217],"document-to-document":[3],"(Doc2Doc)":[4],"neural":[5],"machine":[6],"translation":[7,232],"(NMT)":[8],"via":[9],"Transformer":[10,75],"from":[11],"scratch,":[12],"especially":[13],"on":[14,200,221,245],"small":[15],"datasets,":[16],"usually":[17],"fails":[18],"to":[19,77,179],"converge.":[20],"Our":[21],"dedicated":[22],"probing":[23],"tasks":[24],"show":[25,193],"that":[26,194,225],"1)":[27],"both":[28,79,87,104,235],"the":[29,45,51,61,80,101,146,159,165,201,231],"absolute":[30,54,81,94],"position":[31,34,55,84,98,121,130,138],"and":[32,49,82,89,107,132,162,183,213,215,237],"relative":[33,83,120],"information":[35,56,85],"gets":[36],"gradually":[37],"weakened":[38],"or":[39,142],"even":[40],"vanished":[41],"once":[42],"it":[43],"reaches":[44],"upper":[46],"encoder":[47,58],"layers,":[48],"2)":[50],"vanishing":[52],"of":[53,64,190],"in":[57,86,105,123,168,206,234],"output":[59],"causes":[60],"failure":[63],"Doc2Doc":[65,152,191,227],"NMT.":[66],"To":[67],"alleviate":[68],"this":[69],"problem,":[70],"we":[71,92,117,149],"propose":[72],"position-aware":[74],"(P-Transformer)":[76],"enhance":[78],"self-attention":[88,106],"cross-attention.":[90],"Specifically,":[91],"integrate":[93,119],"positional":[95],"information,":[96],"i.e.,":[97],"embeddings,":[99],"into":[100],"query-key":[102],"pairs":[103],"cross-attention":[108],"through":[109],"simple":[111],"yet":[112],"effective":[113],"addition":[114],"operation.":[115],"Moreover,":[116],"also":[118],"encoding":[122,131],"self-attention.":[124],"The":[125],"proposed":[126],"P-Transformer":[127,175,195],"utilizes":[128],"sinusoidal":[129],"does":[133],"not":[134],"require":[135],"any":[136],"task-specified":[137],"embedding,":[139,141],"segment":[140],"attention":[143],"mechanism.":[144],"Through":[145],"above":[147],"methods,":[148],"build":[150],"NMT":[153,192,228],"model":[154],"with":[155],"P-Transformer,":[156],"which":[157],"ingests":[158],"source":[160],"document":[161,167],"completely":[163],"generates":[164],"target":[166],"sequence-to-sequence":[170],"(seq2seq)":[171],"way.":[172],"In":[173],"addition,":[174],"can":[176],"be":[177],"applied":[178],"seq2seq-based":[180],"document-to-sentence":[181],"(Doc2Sent)":[182],"sentence-to-sentence":[184],"(Sent2Sent)":[185],"translations.":[186],"Extensive":[187],"experimental":[188],"results":[189],"significantly":[196],"outperforms":[197],"strong":[198],"baselines":[199],"widely-used":[202],"9":[203],"document-level":[204],"datasets":[205],"7":[207],"language":[208],"pairs,":[209],"covering":[210],"small-,":[211],"middle-,":[212],"large-scales,":[214],"achieves":[216],"new":[218],"state-of-the-art.":[219],"Experimentation":[220],"discourse":[222,238],"phenomena":[223],"shows":[224],"our":[226,242],"models":[229],"improve":[230],"quality":[233],"BLEU":[236],"coherence.":[239],"We":[240],"make":[241],"code":[243],"available":[244],"Github.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}