Natural reading orders of words are crucial for information extraction from form-like documents. Despite recent advances in Graph Convolutional Networks (GCNs) on modeling spatial layout patterns of documents, they have limited ability to capture reading orders of given word-level node representations in a graph. We propose Reading Order Equivariant Positional Encoding (ROPE), a new positional encoding technique designed to apprehend the sequential presentation of words in documents. ROPE generates unique reading order codes for neighboring words relative to the target word given a word-level graph connectivity. We study two fundamental document entity extraction tasks including word labeling and word grouping on the public FUNSD dataset and a large-scale payment dataset. We show that ROPE consistently improves existing GCNs with a margin up to 8.4% F1-score.
@article{arxiv.2106.10786,
title = {ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction},
author = {Chen-Yu Lee and Chun-Liang Li and Chu Wang and Renshen Wang and Yasuhisa Fujii and Siyang Qin and Ashok Popat and Tomas Pfister},
journal= {arXiv preprint arXiv:2106.10786},
year = {2021}
}