ACL2024

3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding

Yihao Ding, Lorenzo Vaiani, Soyeon Caren Han, Jean Lee, Paolo Garza, Josiah Poon, Luca Cagliero

被引用 5 次

摘要

This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both finegrained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new intra-grained and crossgrained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised understanding of form documents. Through a comprehensive evaluation across publicly available form document understanding datasets, our proposed model consistently outperforms existing baselines, showcasing its efficacy in handling the intricate structures and content of visually complex form documents 1 .