Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documents

Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output depending on the fidelity of the scanned documents. In this pa...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-08
Main Authors: Gupte, Amit, Romanov, Alexey, Mantravadi, Sahitya, Banda, Dalitso, Liu, Jianjie, Khan, Raza, Lakshmanan Ramu Meenal, Han, Benjamin, Srinivasan, Soundar
Format: Article
Language:English
Subjects:
Accuracy
Degradation
Digitization
Natural language processing
Optical character recognition
Optical data processing
Synthesis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output depending on the fidelity of the scanned documents. In this paper, we demonstrate an effective framework for mitigating OCR errors for any downstream NLP task, using Named Entity Recognition (NER) as an example. We first address the data scarcity problem for model training by constructing a document synthesis pipeline, generating realistic but degraded data with NER labels. We measure the NER accuracy drop at various degradation levels and show that a text restoration model, trained on the degraded data, significantly closes the NER accuracy gaps caused by OCR errors, including on an out-of-domain dataset. For the benefit of the community, we have made the document synthesis pipeline available as an open-source project.
ISSN:2331-8422