DI-2021 @ KDD 2021: Best Paper Award
Please join us in congratulating Nguyễn Sinh, Bach Tran, Tuan Anh Nguyen Dang, Duc Nguyen and Hung Le in receiving the Best Paper Award in Document Intelligence Workshop @ KDD 2021!
Title: HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System https://document-intelligence.github.io/DI-2021/papers/#paper_8
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.
- DI2021 Accepted Papers/Posters: https://document-intelligence.github.io/DI-2021/papers/
- DI2021 Program: https://document-intelligence.github.io/DI-2021/program/
Program committee (alphabetical): Doug Burdick, Dave Lewis, Yijuan Lu, Hamid Motahari, Sandeep Tata Chair: Benjamin Han
Originally posted on LinkedIn.