{"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/multimodal-attention-for-neural-machine","title":"Multimodal Attention for Neural Machine Translation","arxiv_id":"1609.03976","date":"2016-09-13","proceeding":null,"authors":["Ozan Caglayan","Loïc Barrault","Fethi Bougares"],"abstract":"The attention mechanism is an important part of the neural machine\ntranslation (NMT) where it was reported to produce richer source representation\ncompared to fixed-length encoding sequence-to-sequence models. Recently, the\neffectiveness of attention has also been explored in the context of image\ncaptioning. In this work, we assess the feasibility of a multimodal attention\nmechanism that simultaneously focus over an image and its natural language\ndescription for generating a description in another language. We train several\nvariants of our proposed attention mechanism on the Multi30k multilingual image\ncaptioning dataset. We show that a dedicated attention for each modality\nachieves up to 1.6 points in BLEU and METEOR compared to a textual NMT\nbaseline.","url_abs":"http://arxiv.org/abs/1609.03976v1","url_pdf":"http://arxiv.org/pdf/1609.03976v1.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":"multimodal-attention-for-neural-machine","repo_url":"https://github.com/lium-lst/nmtpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.03976","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}