{"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/m3p-learning-universal-representations-via","title":"M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training","arxiv_id":"2006.02635","date":"2020-06-04","proceeding":"CVPR 2021 1","authors":["Minheng Ni","Haoyang Huang","Lin Su","Edward Cui","Taroon Bharti","Lijuan Wang","Jianfeng Gao","Dongdong Zhang","Nan Duan"],"abstract":"We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.","url_abs":"https://arxiv.org/abs/2006.02635v4","url_pdf":"https://arxiv.org/pdf/2006.02635v4.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":"m3p-learning-universal-representations-via","repo_url":"https://github.com/microsoft/M3P","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multimodal-machine-translation","task_name":"Multimodal Machine Translation"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.02635","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}