Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
This work addresses the problem of accurately representing and utilizing layout reading order for improving performance in visually-rich document understanding tasks for anyone working with document intelligence.
This paper proposes modeling layout reading order in visually-rich documents as ordering relations rather than a permutation of elements, arguing that this captures more complete information. They establish a benchmark dataset and a relation-extraction-based method for reading order prediction, which outperforms previous methods. Furthermore, they introduce a pipeline that enhances downstream VrD tasks, achieving SOTA results on two task settings and improving performance across three models and eight cross-domain VrD-IE/QA tasks.
Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Previous works typically formulated layout reading order as a permutation of layout elements, i.e. a sequence containing all the layout elements. However, we argue that this formulation does not adequately convey the complete reading order information in the layout, which may potentially lead to performance decline in downstream VrD tasks. To address this issue, we propose to model the layout reading order as ordering relations over the set of layout elements, which have sufficient expressive capability for the complete reading order information. To enable empirical evaluation on methods towards the improved form of reading order prediction (ROP), we establish a comprehensive benchmark dataset including the reading order annotation as relations over layout elements, together with a relation-extraction-based method that outperforms previous methods. Moreover, to highlight the practical benefits of introducing the improved form of layout reading order, we propose a reading-order-relation-enhancing pipeline to improve model performance on any arbitrary VrD task by introducing additional reading order relation inputs. Comprehensive results demonstrate that the pipeline generally benefits downstream VrD tasks: (1) with utilizing the reading order relation information, the enhanced downstream models achieve SOTA results on both two task settings of the targeted dataset; (2) with utilizing the pseudo reading order information generated by the proposed ROP model, the performance of the enhanced models has improved across all three models and eight cross-domain VrD-IE/QA task settings without targeted optimization.