{"id":"https://openalex.org/W4385569940","doi":"https://doi.org/10.18653/v1/2023.acl-long.329","title":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","display_name":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385569940","doi":"https://doi.org/10.18653/v1/2023.acl-long.329"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.329","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.329","pdf_url":"https://aclanthology.org/2023.acl-long.329.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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.acl-long.329.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055815455","display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hao Fei","raw_affiliation_strings":["Sea-NExT Joint Lab, School of Computing, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Sea-NExT Joint Lab, School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318597","display_name":"Qian Liu","orcid":"https://orcid.org/0000-0003-2282-4572"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qian Liu","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["Sea-NExT Joint Lab, School of Computing, National University of Singapore","Harbin Institute of Technology (Shenzhen)"],"affiliations":[{"raw_affiliation_string":"Sea-NExT Joint Lab, School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055815455"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":5.3314,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96928337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5980","last_page":"5994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8157361745834351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7180567979812622},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6916446089744568},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5088541507720947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5069730281829834},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.48752686381340027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4516229033470154},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44752442836761475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43633729219436646},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4260648190975189},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41411957144737244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3706624507904053},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3303762674331665},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11413291096687317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157361745834351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7180567979812622},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6916446089744568},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5088541507720947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5069730281829834},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48752686381340027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4516229033470154},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44752442836761475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43633729219436646},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4260648190975189},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41411957144737244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3706624507904053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3303762674331665},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11413291096687317},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.329","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.329","pdf_url":"https://aclanthology.org/2023.acl-long.329.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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.329","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.329","pdf_url":"https://aclanthology.org/2023.acl-long.329.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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4330972969","display_name":null,"funder_award_id":"62176180","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385569940.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1902237438","https://openalex.org/W2077069816","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2250378130","https://openalex.org/W2257408573","https://openalex.org/W2277195237","https://openalex.org/W2509282593","https://openalex.org/W2512924740","https://openalex.org/W2513263213","https://openalex.org/W2573834658","https://openalex.org/W2595715041","https://openalex.org/W2600702321","https://openalex.org/W2745461083","https://openalex.org/W2786464815","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2962824887","https://openalex.org/W2962830144","https://openalex.org/W2963101956","https://openalex.org/W2963184176","https://openalex.org/W2963216553","https://openalex.org/W2963536419","https://openalex.org/W2963762755","https://openalex.org/W2963909453","https://openalex.org/W2970632400","https://openalex.org/W2980216782","https://openalex.org/W2995558462","https://openalex.org/W3006381853","https://openalex.org/W3035313462","https://openalex.org/W3103544486","https://openalex.org/W3166396011","https://openalex.org/W3175362188","https://openalex.org/W3176395632","https://openalex.org/W3190684574","https://openalex.org/W4221155857","https://openalex.org/W4298393544","https://openalex.org/W4312471667","https://openalex.org/W4385245566","https://openalex.org/W4385573828"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,33,66],"investigate":[4],"a":[5,54,68],"more":[6],"realistic":[7],"unsupervised":[8,92],"multimodal":[9],"machine":[10],"translation":[11,93],"(UMMT)":[12],"setup,":[13,115],"inference-time":[14],"image-free":[15],"UMMT,":[16],"where":[17,48],"the":[18,35,41,58,80,96,104,112,139],"model":[19,136],"is":[20],"trained":[21],"with":[22,28,40,119],"source-text":[23,30],"image":[24],"pairs,":[25],"and":[26,38,43,114,123],"tested":[27],"only":[29],"inputs.":[31],"First,":[32],"represent":[34],"input":[36,63],"images":[37],"texts":[39],"visual":[42,69,77],"language":[44],"scene":[45,70],"graphs":[46],"(SG),":[47],"such":[49],"fine-grained":[50],"vision-language":[51],"features":[52],"ensure":[53],"holistic":[55],"understanding":[56],"of":[57],"semantics.":[59],"To":[60],"enable":[61],"pure-text":[62],"during":[64],"inference,":[65],"devise":[67],"hallucination":[71],"mechanism":[72],"that":[73],"dynamically":[74],"generates":[75],"pseudo":[76],"SG":[78],"from":[79],"given":[81],"textual":[82],"SG.":[83],"Several":[84],"SG-pivoting":[85],"based":[86],"learning":[87],"objectives":[88],"are":[89],"introduced":[90],"for":[91],"training.":[94],"On":[95],"benchmark":[97],"Multi30K":[98],"data,":[99],"our":[100,135],"SG-based":[101],"method":[102],"outperforms":[103],"best-performing":[105],"baseline":[106],"by":[107],"significant":[108],"BLEU":[109],"scores":[110],"on":[111,127],"task":[113,140],"helping":[116],"yield":[117],"translations":[118],"better":[120],"completeness,":[121],"relevance":[122],"fluency":[124],"without":[125],"relying":[126],"paired":[128],"images.":[129],"Further":[130],"in-depth":[131],"analyses":[132],"reveal":[133],"how":[134],"advances":[137],"in":[138],"setting.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":9}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}