{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/latent-visual-cues-for-neural-machine","title":"Latent Variable Model for Multi-modal Translation","arxiv_id":"1811.00357","date":"2018-11-01","proceeding":"ACL 2019 7","authors":["Iacer Calixto","Miguel Rios","Wilker Aziz"],"abstract":"In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong baselines, including a multi-task learning approach (Elliott and K\\'ad\\'ar, 2017) and a conditional variational auto-encoder approach (Toyama et al., 2016). Finally, we show improvements due to (i) predicting image features in addition to only conditioning on them, (ii) imposing a constraint on the minimum amount of information encoded in the latent variable, and (iii) by training on additional target-language image descriptions (i.e. synthetic data).","url_abs":"https://arxiv.org/abs/1811.00357v2","url_pdf":"https://arxiv.org/pdf/1811.00357v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"latent-visual-cues-for-neural-machine","repo_url":"https://github.com/iacercalixto/variational_mmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"multimodal-machine-translation","task_name":"Multimodal Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-machine-translation-on-multi30k","task":"Multimodal Machine Translation","dataset":"Multi30K","model":"VMMTF","rank_in_archive_order":9,"of":15,"metrics":{"BLEU (EN-DE)":"37.6","Meteor (EN-DE)":"56.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.00357","atlas_url":"https://app.syntology.ai/?focus=1811.00357","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}