@article{kim-etal-2026-mmcig,
    title = "{MMCIG}: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling",
    author = "Kim, Hyeyeon  and
      Han, Sungwoo  and
      Kwon, Jingun  and
      Kamigaito, Hidetaka  and
      Okumura, Manabu",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.719/",
    pages = "9150--9161",
    abstract = "In this study, we introduce a novel cover image generation task that produces both a concise summary and a visually corresponding image from a text-only document. Because no existing datasets are available for this task, we propose a multimodal pseudo-labeling method to construct high-quality datasets at low cost. We first collect documents with summaries, multiple images, and captions, and then exclude factually inconsistent instances. Our approach selects one image from multiple images accompanying each document. Using the gold summary, we independently rank both the images and their captions. Then, we annotate a pseudo-label for an image when both the image and its corresponding caption are ranked first in their respective rankings. Finally, we remove documents that contain direct image references within texts. Experimental results demonstrate that the proposed multimodal pseudo-labeling method constructs more precise datasets and generates higher quality images than text- and image-only pseudo-labeling methods, which consider captions and images separately."
}