{"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/fluency-guided-cross-lingual-image-captioning","title":"Fluency-Guided Cross-Lingual Image Captioning","arxiv_id":"1708.04390","date":"2017-08-15","proceeding":null,"authors":["Weiyu Lan","Xirong Li","Jianfeng Dong"],"abstract":"Image captioning has so far been explored mostly in English, as most\navailable datasets are in this language. However, the application of image\ncaptioning should not be restricted by language. Only few studies have been\nconducted for image captioning in a cross-lingual setting. Different from these\nworks that manually build a dataset for a target language, we aim to learn a\ncross-lingual captioning model fully from machine-translated sentences. To\nconquer the lack of fluency in the translated sentences, we propose in this\npaper a fluency-guided learning framework. The framework comprises a module to\nautomatically estimate the fluency of the sentences and another module to\nutilize the estimated fluency scores to effectively train an image captioning\nmodel for the target language. As experiments on two bilingual\n(English-Chinese) datasets show, our approach improves both fluency and\nrelevance of the generated captions in Chinese, but without using any manually\nwritten sentences from the target language.","url_abs":"http://arxiv.org/abs/1708.04390v1","url_pdf":"http://arxiv.org/pdf/1708.04390v1.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":"fluency-guided-cross-lingual-image-captioning","repo_url":"https://github.com/weiyuk/fluent-cap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04390","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}