{"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/using-artificial-tokens-to-control-languages","title":"Using Artificial Tokens to Control Languages for Multilingual Image Caption Generation","arxiv_id":"1706.06275","date":"2017-06-20","proceeding":null,"authors":["Satoshi Tsutsui","David Crandall"],"abstract":"Recent work in computer vision has yielded impressive results in\nautomatically describing images with natural language. Most of these systems\ngenerate captions in a sin- gle language, requiring multiple language-specific\nmodels to build a multilingual captioning system. We propose a very simple\ntechnique to build a single unified model across languages, using artificial\ntokens to control the language, making the captioning system more compact. We\nevaluate our approach on generating English and Japanese captions, and show\nthat a typical neural captioning architecture is capable of learning a single\nmodel that can switch between two different languages.","url_abs":"http://arxiv.org/abs/1706.06275v1","url_pdf":"http://arxiv.org/pdf/1706.06275v1.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":"using-artificial-tokens-to-control-languages","repo_url":"https://github.com/chetangr/Speech-Image-Captioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}