{"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/defoiling-foiled-image-captions","title":"Defoiling Foiled Image Captions","arxiv_id":"1805.06549","date":"2018-05-16","proceeding":"NAACL 2018 6","authors":["Pranava Madhyastha","Josiah Wang","Lucia Specia"],"abstract":"We address the task of detecting foiled image captions, i.e. identifying\nwhether a caption contains a word that has been deliberately replaced by a\nsemantically similar word, thus rendering it inaccurate with respect to the\nimage being described. Solving this problem should in principle require a\nfine-grained understanding of images to detect linguistically valid\nperturbations in captions. In such contexts, encoding sufficiently descriptive\nimage information becomes a key challenge. In this paper, we demonstrate that\nit is possible to solve this task using simple, interpretable yet powerful\nrepresentations based on explicit object information. Our models achieve\nstate-of-the-art performance on a standard dataset, with scores exceeding those\nachieved by humans on the task. We also measure the upper-bound performance of\nour models using gold standard annotations. Our analysis reveals that the\nsimpler model performs well even without image information, suggesting that the\ndataset contains strong linguistic bias.","url_abs":"http://arxiv.org/abs/1805.06549v1","url_pdf":"http://arxiv.org/pdf/1805.06549v1.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":"defoiling-foiled-image-captions","repo_url":"https://github.com/sheffieldnlp/foildataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}