A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents
This work addresses relation extraction for document understanding, but it is incremental as it builds on existing multimodal models.
The paper tackles the under-studied problem of relation extraction in visually-rich documents by proposing a LayoutLMv3-based model that matches or outperforms state-of-the-art results on FUNSD and CORD datasets, with fewer parameters and no specific pre-training.
Document Understanding is an evolving field in Natural Language Processing (NLP). In particular, visual and spatial features are essential in addition to the raw text itself and hence, several multimodal models were developed in the field of Visual Document Understanding (VDU). However, while research is mainly focused on Key Information Extraction (KIE), Relation Extraction (RE) between identified entities is still under-studied. For instance, RE is crucial to regroup entities or obtain a comprehensive hierarchy of data in a document. In this paper, we present a model that, initialized from LayoutLMv3, can match or outperform the current state-of-the-art results in RE applied to Visually-Rich Documents (VRD) on FUNSD and CORD datasets, without any specific pre-training and with fewer parameters. We also report an extensive ablation study performed on FUNSD, highlighting the great impact of certain features and modelization choices on the performances.