{"id":"https://openalex.org/W4412887971","doi":"https://doi.org/10.18653/v1/2025.findings-acl.828","title":"SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation","display_name":"SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887971","doi":"https://doi.org/10.18653/v1/2025.findings-acl.828"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.828.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003447928","display_name":"Ting Xu","orcid":"https://orcid.org/0000-0001-6123-9814"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ting Xu","raw_affiliation_strings":["The Chinese University of Hong Kong , \u2663 Bytedance ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , \u2663 Bytedance ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547686","display_name":"Zhichao Huang","orcid":"https://orcid.org/0000-0002-7662-5184"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhichao Huang","raw_affiliation_strings":["The Chinese University of Hong Kong , \u2663 Bytedance ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , \u2663 Bytedance ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424688","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0001-5633-1739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiankai Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046413480","display_name":"Shanbo Cheng","orcid":"https://orcid.org/0000-0002-6115-9483"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanbo Cheng","raw_affiliation_strings":["\u2662 Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2662 Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111426224","display_name":"Wai Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["\u2662 Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2662 Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4041,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80535812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"16107","last_page":"16123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9657999873161316,"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/machine-translation","display_name":"Machine translation","score":0.6918384432792664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815961599349976},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5215332508087158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711787164211273},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33288177847862244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15842720866203308},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06708693504333496}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6918384432792664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815961599349976},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5215332508087158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711787164211273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33288177847862244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15842720866203308},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06708693504333496},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887971.pdf","grobid_xml":"https://content.openalex.org/works/W4412887971.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"We":[0],"present":[1],"Sequential":[2],"Policy":[3],"Optimization":[4],"for":[5,94],"Simultaneous":[6],"Machine":[7],"Translation":[8],"(SeqPO-SiMT),":[9],"a":[10,24,30,83,200],"new":[11],"policy":[12],"optimization":[13],"framework":[14,70],"that":[15,105,191],"defines":[16],"the":[17,65,72,79,119,132,138,153,163],"simultaneous":[18],"machine":[19],"translation":[20,35,111,165],"(SiMT)":[21],"task":[22],"as":[23,51],"sequential":[25],"decision":[26],"making":[27],"problem,":[28],"incorporating":[29],"tailored":[31,84],"reward":[32],"to":[33,41,75],"enhance":[34],"quality":[36,112],"while":[37,130],"reducing":[38,131],"latency.In":[39,115],"contrast":[40],"popular":[42],"Reinforcement":[43],"Learning":[44],"from":[45,91],"Human":[46],"Feedback":[47],"(RLHF)":[48],"methods,":[49],"such":[50],"PPO":[52],"and":[53,77,98,171],"DPO,":[54],"which":[55],"are":[56],"typically":[57],"applied":[58],"in":[59,128,137,197],"single-step":[60],"tasks,":[61,103],"SeqPO-SiMT":[62,106,117,157],"effectively":[63],"tackles":[64],"multi-step":[66],"SiMT":[67,73,80,102,144,154],"task.This":[68],"intuitive":[69],"allows":[71],"LLMs":[74],"simulate":[76],"refine":[78],"process":[81],"using":[82],"reward.We":[85],"conduct":[86],"experiments":[87],"on":[88,158],"six":[89],"datasets":[90],"diverse":[92],"domains":[93],"En":[95,101,140],"\u2192":[96,100,141],"Zh":[97,99,142],"demonstrating":[104],"consistently":[107],"achieves":[108],"significantly":[109],"higher":[110],"with":[113,146],"lower":[114],"particular,":[116],"outperforms":[118],"supervised":[120],"fine-tuning":[121],"(SFT)":[122],"model":[123],"by":[124,135],"1.13":[125],"\u2021":[126],"points":[127],"COMET,":[129],"Average":[133],"Lagging":[134],"6.17":[136],"NEWSTEST2021":[139],"dataset.While":[143],"operates":[145],"far":[147],"less":[148],"context":[149],"than":[150],"offline":[151,164],"translation,":[152],"results":[155],"of":[156,166,194],"7B":[159],"LLM":[160],"surprisingly":[161],"rival":[162],"high-performing":[167],"LLMs,":[168],"including":[169],"Qwen-2.5-7B-Instruct":[170],"LLaMA-3-8B-Instruct.":[172],"\u2020":[173],"Corresponding":[174],"authors.*":[175],"Work":[176],"done":[177],"when":[178],"Ting":[179],"Xu":[180],"was":[181],"interned":[182],"at":[183],"Bytedance.\u2021":[184],"Kocmi":[185],"et":[186],"al.":[187],"(2024b)":[188],"has":[189],"indicated":[190],"an":[192],"increase":[193],"1":[195],"point":[196],"COMET":[198],"represents":[199],"significant":[201],"improvement.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}