BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding

Abstract

For understanding generic documents, information like font sizes, column layout, and generally the positioning of words may carry semantic information that is crucial for solving a downstream document intelligence task. Our novel BERTgrid, which is based on Chargrid by Katti et al. (2018), represents a document as a grid of contextualized word piece embedding vectors, thereby making its spatial structure and semantics accessible to the processing neural network. The contextualized embedding vectors are retrieved from a BERT language model. We use BERTgrid in combination with a fully convolutional network on a semantic instance segmentation task for extracting fields from invoices. We demonstrate its performance on tabulated line item and document header field extraction.

4 pages, accepted at the "Document Intelligence" workshop of 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

References in corpus (1)

• CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor

Cited by in corpus (6)

• A Survey of Deep Learning Approaches for OCR and Document Understanding
• StrucTexT: Structured Text Understanding with Multi-Modal Transformers
• Efficient Document Image Classification Using Region-Based Graph Neural Network
• Key Information Extraction From Documents: Evaluation And Generator
• One-shot Key Information Extraction from Document with Deep Partial Graph Matching
• Data-Efficient Information Extraction from Form-Like Documents