paper-with-me

Papers

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

2021-08-06 · Amit Gupte, Alexey Romanov, Sahitya Mantravadi, Dalitso Banda, Jianjie Liu, Raza Khan, Lakshmanan Ramu Meenal, Benjamin Han, Soundar Srinivasan

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.

📄 PDF Abstract BibTeX arXiv:2108.02899

Code (1)

microsoft/genalog 공식 구현

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NEROptical Character RecognitionOptical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

The ATLAS of Traffic Lights: A Reliable Perception Framework for Autonomous Driving

2025-04-28 · Rupert Polley, Nikolai Polley, Dominik Heid, Marc Heinrich 외

Traffic light perception is an essential component of the camera-based perception system for autonomous vehicles, enabling accurate detection and interpretation of traffic lights to ensure safe navigation through complex…

Autonomous DrivingAutonomous Vehicles

Action Recognition: From Static Datasets to Moving Robots

2017-01-18 · Fahimeh Rezazadegan, Sareh Shirazi, Ben Upcroft, Michael Milford

Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationa…

Action RecognitionTemporal Action Localization

Generating Notifications for Missing Actions: Don't Forget to Turn the Lights Off!

2015-12-01 · ICCV 2015 12 · Bilge Soran, Ali Farhadi, Linda Shapiro

We all have experienced forgetting habitual actions among our daily activities. For example, we probably have forgotten to turn the lights off before leaving a room or turn the stove off after cooking. In this paper, we …

Prediction

Seeing Temporal Modulation of Lights From Standard Cameras

2018-06-01 · CVPR 2018 6 · Naoki Sakakibara, Fumihiko Sakaue, Jun Sato

In this paper, we propose a novel method for measuring the temporal modulation of lights by using off-the-shelf cameras. In particular, we show that the invisible flicker patterns of various lights such as fluorescent li…

Deblurring

Techno-Economic analysis for Smart Hangar inspection operations through Sensing and Localisation at scale

2025-09-24 · Angelos Plastropoulos, Nicolas P. Avdelidis, Argyrios Zolotas arxiv

The accuracy, resilience, and affordability of localisation are fundamental to autonomous robotic inspection within aircraft maintenance and overhaul (MRO) hangars. Hangars typically feature tall ceilings and are often m…