Syntax-Aware Network for Handwritten Mathematical Expression Recognition

TL;DR

This paper introduces a syntax-aware neural network for handwritten mathematical expression recognition that models expressions as parse trees, significantly improving accuracy over previous character-to-character methods.

Contribution

It is the first to incorporate syntax information via grammar rules and tree traversal modeling into an encoder-decoder network for HMER, reducing structural prediction errors.

Findings

Achieved better recognition performance on three benchmark datasets.

Created a large-scale dataset with 100k handwritten expressions from 10,000 writers.

Demonstrated the effectiveness of syntax modeling in HMER.

Abstract

Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods adhere to the paradigm that the prediction is made "from one character to another", which inevitably yields prediction errors due to the complicated structures of mathematical expressions or crabbed handwritings. In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network. Specifically, we present a set of grammar rules for converting the LaTeX markup sequence of each expression into a parsing tree; then, we model the markup sequence prediction as a tree traverse process with a deep neural network. In this way, the proposed method can effectively describe the syntax context of expressions, alleviating the structure prediction errors of HMER. Experiments on three benchmark datasets demonstrate that our method achieves better recognition performance than prior arts. To further validate the effectiveness of our method, we create a large-scale dataset consisting of 100k handwritten mathematical expression images acquired from ten thousand writers. The source code, new dataset, and pre-trained models of this work will be publicly available.