{"ID":2891000,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18562","arxiv_id":"2507.18562","title":"GIIFT: Graph-guided Inductive Image-free Multimodal Machine Translation","abstract":"Multimodal Machine Translation (MMT) has demonstrated the significant help of visual information in machine translation. However, existing MMT methods face challenges in leveraging the modality gap by enforcing rigid visual-linguistic alignment whilst being confined to inference within their trained multimodal domains. In this work, we construct novel multimodal scene graphs to preserve and integrate modality-specific information and introduce GIIFT, a two-stage Graph-guided Inductive Image-Free MMT framework that uses a cross-modal Graph Attention Network adapter to learn multimodal knowledge in a unified fused space and inductively generalize it to broader image-free translation domains. Experimental results on the Multi30K dataset of English-to-French and English-to-German tasks demonstrate that our GIIFT surpasses existing approaches and achieves the state-of-the-art, even without images during inference. Results on the WMT benchmark show significant improvements over the image-free translation baselines, demonstrating the strength of GIIFT towards inductive image-free inference.","short_abstract":"Multimodal Machine Translation (MMT) has demonstrated the significant help of visual information in machine translation. However, existing MMT methods face challenges in leveraging the modality gap by enforcing rigid visual-linguistic alignment whilst being confined to inference within their trained multimodal domains....","url_abs":"https://arxiv.org/abs/2507.18562","url_pdf":"https://arxiv.org/pdf/2507.18562v2","authors":"[\"Jiafeng Xiong\",\"Yuting Zhao\"]","published":"2025-07-24T16:36:47Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[]","has_code":false}