English

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization

Computer Vision and Pattern Recognition 2024-08-07 v1 Computation and Language

Abstract

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity of content within multimodal inputs and outputs presents a significant challenge to the execution of MSMO. Traditional approaches typically adopt a holistic perspective on coarse image-text data or individual visual objects, overlooking the essential connections between objects and the entities they represent. To integrate the fine-grained entity knowledge, we propose an Entity-Guided Multimodal Summarization model (EGMS). Our model, building on BART, utilizes dual multimodal encoders with shared weights to process text-image and entity-image information concurrently. A gating mechanism then combines visual data for enhanced textual summary generation, while image selection is refined through knowledge distillation from a pre-trained vision-language model. Extensive experiments on public MSMO dataset validate the superiority of the EGMS method, which also prove the necessity to incorporate entity information into MSMO problem.

Keywords

Cite

@article{arxiv.2408.03149,
  title  = {Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization},
  author = {Yanghai Zhang and Ye Liu and Shiwei Wu and Kai Zhang and Xukai Liu and Qi Liu and Enhong Chen},
  journal= {arXiv preprint arXiv:2408.03149},
  year   = {2024}
}

Comments

In ACL-Findings 2024

R2 v1 2026-06-28T18:05:21.823Z