{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multimodal-machine-translation","name":"Multimodal Machine Translation","slug":"multimodal-machine-translation","description_markdown":"Multimodal machine translation is the task of doing machine translation with multiple data sources - for example, translating \"a bird is flying over water\" + an image of a bird over water to German text.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Findings of the Third Shared Task on Multimodal Machine Translation](https://www.aclweb.org/anthology/W18-6402.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":108,"papers_with_code":38,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multimodal-machine-translation-on-multi30k","slug":"multimodal-machine-translation-on-multi30k","dataset":"Multi30K","dataset_url":"/dataset/multi30k","rows_in_archive":15,"metrics":["BLEU (EN-DE)","BLUE (DE-EN)","Meteor (EN-DE)","Meteor (EN-FR)"],"first_row_in_archive_order":{"model":"ERNIE-UniX2","paper_title":"ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation","paper_url":"/paper/ernie-unix2-a-unified-cross-lingual-cross","paper_date":"2022-11-09","arxiv_id":"2211.04861","code_links":[],"syntology":null}},{"leaderboard":"/sota/multimodal-machine-translation-on-hindi-1","slug":"multimodal-machine-translation-on-hindi-1","dataset":"Hindi Visual Genome (Test Set)","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU (EN-HI)"],"first_row_in_archive_order":{"model":"ViTA","paper_title":"ViTA: Visual-Linguistic Translation by Aligning Object Tags","paper_url":"/paper/vita-visual-linguistic-translation-by","paper_date":"2021-06-01","arxiv_id":"2106.00250","code_links":[{"title":"kshitij98/vita","url":"https://github.com/kshitij98/vita"}],"syntology":null}},{"leaderboard":"/sota/multimodal-machine-translation-on-hindi-2","slug":"multimodal-machine-translation-on-hindi-2","dataset":"Hindi Visual Genome (Challenge Set)","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU (EN-HI)"],"first_row_in_archive_order":{"model":"ViTA","paper_title":"ViTA: Visual-Linguistic Translation by Aligning Object Tags","paper_url":"/paper/vita-visual-linguistic-translation-by","paper_date":"2021-06-01","arxiv_id":"2106.00250","code_links":[{"title":"kshitij98/vita","url":"https://github.com/kshitij98/vita"}],"syntology":null}}],"datasets":[{"url":"/dataset/multi30k","name":"Multi30K","full_name":"","num_papers_in_archive":139},{"url":"/dataset/hindi-visual-genome","name":"Hindi Visual Genome","full_name":"","num_papers_in_archive":7},{"url":"/dataset/havg","name":"HaVG","full_name":"Hausa Visual Genome Dataset","num_papers_in_archive":3},{"url":"/dataset/wmt-2016-biomedical","name":"WMT 2016 Biomedical","full_name":"WMT 2016 Biomedical Translation Task","num_papers_in_archive":1},{"url":"/dataset/wmt-2016-it","name":"WMT 2016 IT","full_name":"WMT 2016 IT Translation Task","num_papers_in_archive":1}],"subtasks":[{"url":"/task/face-to-face-translation","name":"Face to Face Translation"},{"url":"/task/multimodal-lexical-translation","name":"Multimodal Lexical Translation"}],"parent_tasks":[{"url":"/task/machine-translation","name":"Machine Translation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":108,"of_with_code":38,"tagged_in_all":108,"counts":{"archive_papers_tagged":108,"with_a_code_link":38,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":108,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","repositories_listed":595,"syntology":{"n":946,"n_ran":610,"n_constructed":293,"n_ran_checked":529,"n_instrument":81,"n_unverified":336,"n_honours":45,"n_violates":15,"n_no_contract":469,"n_pointer_only":451,"phrase":"610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified","sample_list":"/paper/attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/1706.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03762"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/towards-zero-shot-multimodal-machine","slug":"towards-zero-shot-multimodal-machine","title":"Towards Zero-Shot Multimodal Machine Translation","date":"2024-07-18","arxiv_id":"2407.13579","repositories_listed":2,"syntology":null},{"url":"/paper/tackling-ambiguity-with-images-improved","slug":"tackling-ambiguity-with-images-improved","title":"Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation","date":"2022-12-20","arxiv_id":"2212.10140","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tackling-ambiguity-with-images-improved#ran","syntology_url":"https://syntology.ai/paper/2212.10140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10140"}},"official":{"repos":["matthieufp/commute","matthieufp/vgamt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-vision-features-in-multimodal-machine-1","slug":"on-vision-features-in-multimodal-machine-1","title":"On Vision Features in Multimodal Machine Translation","date":"2022-03-17","arxiv_id":"2203.09173","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-vision-features-in-multimodal-machine-1#ran","syntology_url":"https://syntology.ai/paper/2203.09173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09173"}},"official":{"repos":["libeineu/fairseq_mmt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi30k-multilingual-english-german-image","slug":"multi30k-multilingual-english-german-image","title":"Multi30K: Multilingual English-German Image Descriptions","date":"2016-05-02","arxiv_id":"1605.00459","repositories_listed":2,"syntology":null},{"url":"/paper/3am-an-ambiguity-aware-multi-modal-machine","slug":"3am-an-ambiguity-aware-multi-modal-machine","title":"3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset","date":"2024-04-29","arxiv_id":"2404.18413","repositories_listed":1,"syntology":null},{"url":"/paper/seamless-multilingual-expressive-and","slug":"seamless-multilingual-expressive-and","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","date":"2023-12-08","arxiv_id":"2312.05187","repositories_listed":1,"syntology":null},{"url":"/paper/video-helpful-multimodal-machine-translation","slug":"video-helpful-multimodal-machine-translation","title":"Video-Helpful Multimodal Machine Translation","date":"2023-10-31","arxiv_id":"2310.20201","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-probing-signals-into-multimodal","slug":"incorporating-probing-signals-into-multimodal","title":"Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs","date":"2023-10-26","arxiv_id":"2310.17133","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-between-synthetic-and","slug":"bridging-the-gap-between-synthetic-and","title":"Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation","date":"2023-10-20","arxiv_id":"2310.13361","repositories_listed":1,"syntology":null},{"url":"/paper/cliptrans-transferring-visual-knowledge-with","slug":"cliptrans-transferring-visual-knowledge-with","title":"CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation","date":"2023-08-29","arxiv_id":"2308.15226","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cliptrans-transferring-visual-knowledge-with#ran","syntology_url":"https://syntology.ai/paper/2308.15226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15226"}},"official":{"repos":["devaansh100/cliptrans"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/havqa-a-dataset-for-visual-question-answering","slug":"havqa-a-dataset-for-visual-question-answering","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","date":"2023-05-28","arxiv_id":"2305.17690","repositories_listed":1,"syntology":null},{"url":"/paper/bigvideo-a-large-scale-video-subtitle","slug":"bigvideo-a-large-scale-video-subtitle","title":"BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation","date":"2023-05-23","arxiv_id":"2305.18326","repositories_listed":1,"syntology":null},{"url":"/paper/scene-graph-as-pivoting-inference-time-image","slug":"scene-graph-as-pivoting-inference-time-image","title":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","date":"2023-05-20","arxiv_id":"2305.12256","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-triplet-leveraging-the-most-data-for","slug":"beyond-triplet-leveraging-the-most-data-for","title":"Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation","date":"2022-12-20","arxiv_id":"2212.10313","repositories_listed":1,"syntology":null},{"url":"/paper/distill-the-image-to-nowhere-inversion","slug":"distill-the-image-to-nowhere-inversion","title":"Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation","date":"2022-10-10","arxiv_id":"2210.04468","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/distill-the-image-to-nowhere-inversion#ran","syntology_url":"https://syntology.ai/paper/2210.04468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04468"}},"official":{"repos":["pengr/ikd-mmt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/valhalla-visual-hallucination-for-machine","slug":"valhalla-visual-hallucination-for-machine","title":"VALHALLA: Visual Hallucination for Machine Translation","date":"2022-05-31","arxiv_id":"2206.00100","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/valhalla-visual-hallucination-for-machine#ran","syntology_url":"https://syntology.ai/paper/2206.00100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00100"}},"official":null}},{"url":"/paper/neural-machine-translation-with-phrase-level","slug":"neural-machine-translation-with-phrase-level","title":"Neural Machine Translation with Phrase-Level Universal Visual Representations","date":"2022-03-19","arxiv_id":"2203.10299","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/neural-machine-translation-with-phrase-level#ran","syntology_url":"https://syntology.ai/paper/2203.10299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10299"}},"official":{"repos":["ictnlp/pluvr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/msctd-a-multimodal-sentiment-chat-translation","slug":"msctd-a-multimodal-sentiment-chat-translation","title":"MSCTD: A Multimodal Sentiment Chat Translation Dataset","date":"2022-02-28","arxiv_id":"2202.13645","repositories_listed":1,"syntology":null},{"url":"/paper/visa-an-ambiguous-subtitles-dataset-for","slug":"visa-an-ambiguous-subtitles-dataset-for","title":"VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation","date":"2022-01-20","arxiv_id":"2201.08054","repositories_listed":1,"syntology":null},{"url":"/paper/vision-matters-when-it-should-sanity-checking","slug":"vision-matters-when-it-should-sanity-checking","title":"Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models","date":"2021-09-08","arxiv_id":"2109.03415","repositories_listed":1,"syntology":null},{"url":"/paper/bertgen-multi-task-generation-through-bert","slug":"bertgen-multi-task-generation-through-bert","title":"BERTGEN: Multi-task Generation through BERT","date":"2021-06-07","arxiv_id":"2106.03484","repositories_listed":1,"syntology":null},{"url":"/paper/cultural-and-geographical-influences-on-image","slug":"cultural-and-geographical-influences-on-image","title":"Cultural and Geographical Influences on Image Translatability of Words across Languages","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vita-visual-linguistic-translation-by","slug":"vita-visual-linguistic-translation-by","title":"ViTA: Visual-Linguistic Translation by Aligning Object Tags","date":"2021-06-01","arxiv_id":"2106.00250","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-visual-pre-training-for","slug":"cross-lingual-visual-pre-training-for","title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation","date":"2021-01-25","arxiv_id":"2101.10044","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-context-guided-capsule-network-for","slug":"dynamic-context-guided-capsule-network-for","title":"Dynamic Context-guided Capsule Network for Multimodal Machine Translation","date":"2020-09-04","arxiv_id":"2009.02016","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-transformer-for-multimodal-machine","slug":"multimodal-transformer-for-multimodal-machine","title":"Multimodal Transformer for Multimodal Machine Translation","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-knowledge-distillation-a-simple-way-for","slug":"self-knowledge-distillation-a-simple-way-for","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","date":"2020-06-22","arxiv_id":"2006.12000","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-knowledge-distillation-a-simple-way-for#ran","syntology_url":"https://syntology.ai/paper/2006.12000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12000"}},"official":{"repos":["lgcnsai/ps-kd-pytorch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/m3p-learning-universal-representations-via","slug":"m3p-learning-universal-representations-via","title":"M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training","date":"2020-06-04","arxiv_id":"2006.02635","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-translations-with-visual-awareness","slug":"distilling-translations-with-visual-awareness","title":"Distilling Translations with Visual Awareness","date":"2019-06-18","arxiv_id":"1906.07701","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-machine-translation-with-embedding","slug":"multimodal-machine-translation-with-embedding","title":"Multimodal Machine Translation with Embedding Prediction","date":"2019-04-01","arxiv_id":"1904.00639","repositories_listed":1,"syntology":null},{"url":"/paper/latent-visual-cues-for-neural-machine","slug":"latent-visual-cues-for-neural-machine","title":"Latent Variable Model for Multi-modal Translation","date":"2018-11-01","arxiv_id":"1811.00357","repositories_listed":1,"syntology":null},{"url":"/paper/umons-submission-for-wmt18-multimodal","slug":"umons-submission-for-wmt18-multimodal","title":"UMONS Submission for WMT18 Multimodal Translation Task","date":"2018-10-15","arxiv_id":"1810.06233","repositories_listed":1,"syntology":null},{"url":"/paper/findings-of-the-third-shared-task-on","slug":"findings-of-the-third-shared-task-on","title":"Findings of the Third Shared Task on Multimodal Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-visual-attention-grounding-neural-model-for","slug":"a-visual-attention-grounding-neural-model-for","title":"A Visual Attention Grounding Neural Model for Multimodal Machine Translation","date":"2018-08-24","arxiv_id":"1808.08266","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-lexical-translation","slug":"multimodal-lexical-translation","title":"Multimodal Lexical Translation","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nmtpy-a-flexible-toolkit-for-advanced-neural","slug":"nmtpy-a-flexible-toolkit-for-advanced-neural","title":"NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems","date":"2017-06-01","arxiv_id":"1706.00457","repositories_listed":1,"syntology":null},{"url":"/paper/does-multimodality-help-human-and-machine-for","slug":"does-multimodality-help-human-and-machine-for","title":"Does Multimodality Help Human and Machine for Translation and Image Captioning?","date":"2016-05-30","arxiv_id":"1605.09186","repositories_listed":1,"syntology":null},{"url":null,"slug":"cammt-benchmarking-culturally-aware","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","date":"2025-05-30","arxiv_id":"2505.24456","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-translation-with-visual","title":"Multimodal Machine Translation with Visual Scene Graph Pruning","date":"2025-05-26","arxiv_id":"2505.19507","repositories_listed":0,"syntology":null},{"url":null,"slug":"topicvd-a-topic-based-dataset-of-video-guided","title":"TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries","date":"2025-05-09","arxiv_id":"2505.05714","repositories_listed":0,"syntology":null},{"url":null,"slug":"florenz-scaling-laws-for-systematic","title":"Florenz: Scaling Laws for Systematic Generalization in Vision-Language Models","date":"2025-03-12","arxiv_id":"2503.09443","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-imagination-clearer-stable-diffusion","title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation","date":"2024-12-17","arxiv_id":"2412.12627","repositories_listed":0,"syntology":null},{"url":null,"slug":"emmett-efficient-multimodal-machine","title":"EMMeTT: Efficient Multimodal Machine Translation Training","date":"2024-09-20","arxiv_id":"2409.13523","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-necessity-of-visual-modality-in","title":"Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets","date":"2024-04-09","arxiv_id":"2404.06107","repositories_listed":0,"syntology":null},{"url":null,"slug":"adding-multimodal-capabilities-to-a-text-only","title":"Adding Multimodal Capabilities to a Text-only Translation Model","date":"2024-03-05","arxiv_id":"2403.03045","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-concrete-visual-tokens-for","title":"Detecting Concrete Visual Tokens for Multimodal Machine Translation","date":"2024-03-05","arxiv_id":"2403.03075","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-case-for-evaluating-multimodal","title":"The Case for Evaluating Multimodal Translation Models on Text Datasets","date":"2024-03-05","arxiv_id":"2403.03014","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-adversarial-attack-on-image-guided","title":"Iterative Adversarial Attack on Image-guided Story Ending Generation","date":"2023-05-16","arxiv_id":"2305.13208","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-algorithm-of-multimodal-pre","title":"Generalization algorithm of multimodal pre-training model based on graph-text self-supervised training","date":"2023-02-16","arxiv_id":"2302.10315","repositories_listed":0,"syntology":null},{"url":"/paper/ernie-unix2-a-unified-cross-lingual-cross","slug":"ernie-unix2-a-unified-cross-lingual-cross","title":"ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation","date":"2022-11-09","arxiv_id":"2211.04861","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvp-m3-language-aware-visual-prompt-for","title":"LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation","date":"2022-10-19","arxiv_id":"2210.15461","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-visual-awareness-in-multimodal","title":"Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective","date":"2022-10-16","arxiv_id":"2210.08478","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-visual-attention-for-simultaneous","title":"Supervised Visual Attention for Simultaneous Multimodal Machine Translation","date":"2022-01-23","arxiv_id":"2201.09324","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-vision-features-in-multimodal-machine","title":"On Vision Features in Multimodal Machine Translation","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experiences-of-adapting-multimodal-machine","title":"Experiences of Adapting Multimodal Machine Translation Techniques for Hindi","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-multimodal-neural-machine","title":"Low Resource Multimodal Neural Machine Translation of English-Hindi in News Domain","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-neural-machine-translation-system","title":"Multimodal Neural Machine Translation System for English to Bengali","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"make-the-blind-translator-see-the-world-a","title":"Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rakutens-participation-in-wat-2021-examining","title":"Rakuten’s Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"good-for-misconceived-reasons-an-empirical","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","date":"2021-05-30","arxiv_id":"2105.14462","repositories_listed":0,"syntology":null},{"url":"/paper/gumbel-attention-for-multi-modal-machine","slug":"gumbel-attention-for-multi-modal-machine","title":"Gumbel-Attention for Multi-modal Machine Translation","date":"2021-03-16","arxiv_id":"2103.08862","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-for-misconceived-reasons-revisiting","title":"Good for Misconceived Reasons: Revisiting Neural Multimodal Machine Translation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-object-level-visual-context","title":"Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding","date":"2020-12-18","arxiv_id":"2101.05208","repositories_listed":0,"syntology":null},{"url":null,"slug":"msvd-turkish-a-comprehensive-multimodal","title":"MSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish","date":"2020-12-13","arxiv_id":"2012.07098","repositories_listed":0,"syntology":null},{"url":null,"slug":"tmu-japanese-english-multimodal-machine","title":"TMU Japanese-English Multimodal Machine Translation System for WAT 2020","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/generative-imagination-elevates-machine","slug":"generative-imagination-elevates-machine","title":"Generative Imagination Elevates Machine Translation","date":"2020-09-21","arxiv_id":"2009.09654","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-visually-grounded-parallel-corpus-with","title":"A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-decoders-of-maximum","title":"Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach","date":"2020-03-08","arxiv_id":"2003.03716","repositories_listed":0,"syntology":null},{"url":"/paper/multimodal-machine-translation-through","slug":"multimodal-machine-translation-through","title":"Multimodal Machine Translation through Visuals and Speech","date":"2019-11-28","arxiv_id":"1911.12798","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-fusion-for-multimodal-data","title":"Adaptive Fusion Techniques for Multimodal Data","date":"2019-11-10","arxiv_id":"1911.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-effect-of-textual","title":"Understanding the Effect of Textual Adversaries in Multimodal Machine Translation","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"191013215","title":"Transformer-based Cascaded Multimodal Speech Translation","date":"2019-10-29","arxiv_id":"1910.13215","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-leveraging-the-visual-modality-for-neural","title":"On Leveraging the Visual Modality for Neural Machine Translation","date":"2019-10-07","arxiv_id":"1910.02754","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-representations-learned-by-multimodal","title":"Probing Representations Learned by Multimodal Recurrent and Transformer Models","date":"2019-08-29","arxiv_id":"1908.11125","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-multimodal-machine-translation","title":"Multilingual Multimodal Machine Translation for Dravidian Languages utilizing Phonetic Transcription","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/hindi-visual-genome-a-dataset-for-multimodal","slug":"hindi-visual-genome-a-dataset-for-multimodal","title":"Hindi Visual Genome: A Dataset for Multimodal English-to-Hindi Machine Translation","date":"2019-07-21","arxiv_id":"1907.08948","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-word-sense-translation","title":"Grounded Word Sense Translation","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"debiasingword-embeddings-improves-multimodal","title":"Debiasing Word Embeddings Improves Multimodal Machine Translation","date":"2019-05-24","arxiv_id":"1905.10464","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-need-for-visual-context-in","title":"Probing the Need for Visual Context in Multimodal Machine Translation","date":"2019-03-20","arxiv_id":"1903.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-evaluation-of-multimodal-machine","title":"Adversarial Evaluation of Multimodal Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cuni-system-for-the-wmt18-multimodal-1","title":"CUNI System for the WMT18 Multimodal Translation Task","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/findings-of-the-2018-conference-on-machine","slug":"findings-of-the-2018-conference-on-machine","title":"Findings of the 2018 Conference on Machine Translation (WMT18)","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"input-combination-strategies-for-multi-source","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sheffield-submissions-for-wmt18-multimodal","title":"Sheffield Submissions for WMT18 Multimodal Translation Shared Task","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-afrl-ohio-state-wmt18-multimodal-system","title":"The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-sequence-level-training-for","title":"Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report","date":"2018-08-31","arxiv_id":"1808.10592","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-memad-submission-to-the-wmt18-multimodal","title":"The MeMAD Submission to the WMT18 Multimodal Translation Task","date":"2018-08-31","arxiv_id":"1808.10802","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-attentive-transformer-machine","title":"Doubly Attentive Transformer Machine Translation","date":"2018-07-30","arxiv_id":"1807.11605","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-translation-with","title":"Multimodal Machine Translation with Reinforcement Learning","date":"2018-05-07","arxiv_id":"1805.02356","repositories_listed":0,"syntology":null},{"url":"/paper/a-dataset-and-reranking-method-for-multimodal","slug":"a-dataset-and-reranking-method-for-multimodal","title":"A Dataset and Reranking Method for Multimodal MT of User-Generated Image Captions","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multinews-a-web-collection-of-an-aligned","title":"MultiNews: A Web collection of an Aligned Multimodal and Multilingual Corpus","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-second-shared-task-on","title":"Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description","date":"2017-10-19","arxiv_id":"1710.07177","repositories_listed":0,"syntology":null},{"url":null,"slug":"osu-multimodal-machine-translation-system","title":"OSU Multimodal Machine Translation System Report","date":"2017-10-07","arxiv_id":"1710.02718","repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-2017-conference-on-machine","title":"Findings of the 2017 Conference on Machine Translation (WMT17)","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-image-descriptions-using","title":"Generating Image Descriptions using Multilingual Data","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nict-naist-system-for-wmt17-multimodal","title":"NICT-NAIST System for WMT17 Multimodal Translation Task","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sheffield-multimt-using-object-posterior","title":"Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-afrl-osu-wmt17-multimodal-translation","title":"The AFRL-OSU WMT17 Multimodal Translation System: An Image Processing Approach","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/multimodal-machine-translation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/multimodal-machine-translation/papers/2","json":"/task/multimodal-machine-translation/papers/2.json","rows":8},{"order":"ran","page":1,"of":1,"url":"/task/multimodal-machine-translation/papers/ran/1","json":"/task/multimodal-machine-translation/papers/ran/1.json","rows":7}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e6df08da03b98ec191085b4a31258b543635282660e43af55b517eb791cef018","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}