Problem
Research questions and friction points this paper is trying to address.
handwritten answer sheet
document parsing
handwriting recognition
noisy hybrid document
smart education
HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
🤖 AI Summary
This study addresses the failure of existing datasets caused by mixed text-image-formula layouts and erasure noise in real-world student answer sheets by constructing HANS, the first hybrid document parsing benchmark tailored for educational scenarios. Furthermore, this work proposes NA-GOT, an end-to-end framework that achieves robust recognition under complex noise through fine-grained annotation, a lightweight feature denoising module, and a noise-aware attention mechanism during decoding. Experimental results demonstrate that the proposed dataset presents significant challenges, while NA-GOT yields substantial improvements in both the accuracy and stability of answer process recognition.
📝 Abstract
Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and handwriting recognition benchmarks are predominantly designed for well-structured printed documents or isolated mathematical expressions, lacking datasets that capture the complex characteristics inherent to student answer sheets, including multi-line derivation processes, heterogeneous mixtures of text and mathematical formulae, and noise artifacts such as strikethroughs. To address this gap, we introduce HANS, the first dataset explicitly constructed for real-world educational scenarios, encompassing mathematical expressions, natural language text, hand-drawn tables, and diverse noise patterns including corrections and deletions, accompanied by fine-grained annotations that establish a reliable foundation for robust recognition research. Building upon HANS, we propose NA-GOT, an end-to-end framework that achieves two-stage noise suppression through a lightweight noise suppression module operating at the feature level, complemented by a noiseaware attention mechanism incorporated into the decoding stage. Experimental results demonstrate that HANS poses substantial challenges to existing methods, while NA-GOT achieves significant improvements in both accuracy and stability for answer process recognition. The dataset will be made publicly available upon publication.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Handwritten Answer Sheet Dataset
Noisy Hybrid Document Parsing
End-to-End Framework
Noise Suppression Module
Noise-Aware Attention Mechanism
🔎 Similar Papers
No similar papers found.
