Language, OCR, Form Independent (LOFI) pipeline for Industrial Document Information Extraction
Chang Oh Yoon, Wonbeen Lee, Seokhwan Jang, Kyuwon Choi, Minsung Jung, Daewoo Choi
Abstract
This paper presents LOFI (Language, OCR, Form Independent), a pipeline for Document Information Extraction (DIE) in Low-Resource Language (LRL) business documents. LOFI pipeline solves language, Optical Character Recognition (OCR), and form dependencies through flexible model architecture, a token-level box split algorithm, and the SPADE decoder. Experiments on Korean and Japanese documents demonstrate high performance in Semantic Entity Recognition (SER) task without additional pre-training. The pipeline’s effectiveness is validated through real-world applications in insurance and tax-free declaration services, advancing DIE capabilities for diverse languages and document types in industrial settings.
BibTeX
@inproceedings{yoon-etal-2024-language,
title = "Language, {OCR}, Form Independent ({LOFI}) pipeline for Industrial Document Information Extraction",
author = "Yoon, Chang Oh and
Lee, Wonbeen and
Jang, Seokhwan and
Choi, Kyuwon and
Jung, Minsung and
Choi, Daewoo",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.79/",
doi = "10.18653/v1/2024.emnlp-industry.79",
pages = "1056--1067"
}