{"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/iparaphrasing-extracting-visually-grounded","title":"iParaphrasing: Extracting Visually Grounded Paraphrases via an Image","arxiv_id":"1806.04284","date":"2018-06-12","proceeding":"COLING 2018 8","authors":["Chenhui Chu","Mayu Otani","Yuta Nakashima"],"abstract":"A paraphrase is a restatement of the meaning of a text in other words.\nParaphrases have been studied to enhance the performance of many natural\nlanguage processing tasks. In this paper, we propose a novel task iParaphrasing\nto extract visually grounded paraphrases (VGPs), which are different phrasal\nexpressions describing the same visual concept in an image. These extracted\nVGPs have the potential to improve language and image multimodal tasks such as\nvisual question answering and image captioning. How to model the similarity\nbetween VGPs is the key of iParaphrasing. We apply various existing methods as\nwell as propose a novel neural network-based method with image attention, and\nreport the results of the first attempt toward iParaphrasing.","url_abs":"http://arxiv.org/abs/1806.04284v1","url_pdf":"http://arxiv.org/pdf/1806.04284v1.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":"iparaphrasing-extracting-visually-grounded","repo_url":"https://github.com/ids-cv/coling_iparaphrasing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.04284","atlas_url":"https://app.syntology.ai/?focus=1806.04284","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}