English

Enhancing Complex Formula Recognition with Hierarchical Detail-Focused Network

Computation and Language 2025-01-10 v2

Abstract

Hierarchical and complex Mathematical Expression Recognition (MER) is challenging due to multiple possible interpretations of a formula, complicating both parsing and evaluation. In this paper, we introduce the Hierarchical Detail-Focused Recognition dataset (HDR), the first dataset specifically designed to address these issues. It consists of a large-scale training set, HDR-100M, offering an unprecedented scale and diversity with one hundred million training instances. And the test set, HDR-Test, includes multiple interpretations of complex hierarchical formulas for comprehensive model performance evaluation. Additionally, the parsing of complex formulas often suffers from errors in fine-grained details. To address this, we propose the Hierarchical Detail-Focused Recognition Network (HDNet), an innovative framework that incorporates a hierarchical sub-formula module, focusing on the precise handling of formula details, thereby significantly enhancing MER performance. Experimental results demonstrate that HDNet outperforms existing MER models across various datasets.

Keywords

Cite

@article{arxiv.2409.11677,
  title  = {Enhancing Complex Formula Recognition with Hierarchical Detail-Focused Network},
  author = {Jiale Wang and Junhui Yu and Huanyong Liu and Chenanran Kong},
  journal= {arXiv preprint arXiv:2409.11677},
  year   = {2025}
}

Comments

Accepted to the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025)

R2 v1 2026-06-28T18:48:34.574Z