HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System release_kqfwjpjrjjd73ifge4xs5kubqm

by Bao-Sinh Nguyen, Quang-Bach Tran, Tuan-Anh Nguyen Dang, Duc Nguyen, Hung Le

Released as a article .

2022  

Abstract

Measuring the confidence of AI models is critical for safely deploying AI in real-world industrial systems. One important application of confidence measurement is information extraction from scanned documents. However, there exists no solution to provide reliable confidence score for current state-of-the-art deep-learning-based information extractors. In this paper, we propose a complete and novel architecture to measure confidence of current deep learning models in document information extraction task. Our architecture consists of a Multi-modal Conformal Predictor and a Variational Cluster-oriented Anomaly Detector, trained to faithfully estimate its confidence on its outputs without the need of host models modification. We evaluate our architecture on real-wold datasets, not only outperforming competing confidence estimators by a huge margin but also demonstrating generalization ability to out-of-distribution data.
In text/plain format

Archived Files and Locations

application/pdf  1.8 MB
file_4ycjcvfiazaxbm563wuur63qae
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-06-01
Version   v1
Language   en ?
arXiv  2206.02628v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b015ff51-d394-429a-848a-f682da653ebe
API URL: JSON