TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition

TL;DR

TAMER is a novel Transformer-based model that effectively recognizes handwritten mathematical expressions by jointly modeling sequence and tree structures, leading to improved accuracy and structural correctness.

Contribution

Introduces TAMER, a Tree-aware Transformer that combines sequence and tree decoding for better understanding of mathematical expression structures.

Findings

Outperforms existing models on CROHME datasets

Achieves state-of-the-art accuracy in complex expression recognition

Enhances structural validity of generated LaTeX sequences

Abstract

Handwritten Mathematical Expression Recognition (HMER) has extensive applications in automated grading and office automation. However, existing sequence-based decoding methods, which directly predict $\LaTeX$ sequences, struggle to understand and model the inherent tree structure of $\LaTeX$ and often fail to ensure syntactic correctness in the decoded results. To address these challenges, we propose a novel model named TAMER (Tree-Aware Transformer) for handwritten mathematical expression recognition. TAMER introduces an innovative Tree-aware Module while maintaining the flexibility and efficient training of Transformer. TAMER combines the advantages of both sequence decoding and tree decoding models by jointly optimizing sequence prediction and tree structure prediction tasks, which enhances the model's understanding and generalization of complex mathematical expression structures. During inference, TAMER employs a Tree Structure Prediction Scoring Mechanism to improve the structural validity of the generated $\LaTeX$ sequences. Experimental results on CROHME datasets demonstrate that TAMER outperforms traditional sequence decoding and tree decoding models, especially in handling complex mathematical structures, achieving state-of-the-art (SOTA) performance.