# Improving Chinese Character Representation with Formation Tree

arXiv: https://arxiv.org/abs/2404.12693 · HTML: https://mlsanity.com/paper/2404.12693/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 59 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [Graph-Bert: Only Attention is Needed for Learning Graph Representations](https://mlsanity.com/paper/2001.05140/) (2020)
- [Graph Inductive Biases in Transformers without Message Passing](https://mlsanity.com/paper/2305.17589/) (2023)
- [Rethinking the Expressive Power of GNNs via Graph Biconnectivity](https://mlsanity.com/paper/2301.09505/) (2023)
- [Global Self-Attention as a Replacement for Graph Convolution](https://mlsanity.com/paper/2108.03348/) (2021)
- [Graph Transformer for Graph-to-Sequence Learning](https://mlsanity.com/paper/1911.07470/) (2019)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [Transformers Meet Directed Graphs](https://mlsanity.com/paper/2302.00049/) (2023)
- [Text Recognition in the Wild: A Survey](https://mlsanity.com/paper/2005.03492/) (2020)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning](https://mlsanity.com/paper/2309.01083/) (2023)
- [DenseRAN for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1808.04134/) (2018)
- [Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification](https://mlsanity.com/paper/1309.0261/) (2013)
- [Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1702.07975/) (2017)
- [RZCR: Zero-shot Character Recognition via Radical-based Reasoning](https://mlsanity.com/paper/2207.05842/) (2022)
- [Chinese Character Recognition with Radical-Structured Stroke Trees](https://mlsanity.com/paper/2211.13518/) (2022)

## Built on by (most cited first, 2 of 2)

- [Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition](https://mlsanity.com/paper/2602.03913/) (2026)
- [Zero-Shot Chinese Character Recognition via Global-Local Dual-Branch Alignment and Hierarchical Inference](https://mlsanity.com/paper/2605.08814/) (2026)

## Abstract (arXiv)

Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the inherent sparsity of character usage complicates the generalization of learned representations. Prior research has explored radical-based sequences to overcome these issues, achieving progress in recognizing unseen characters. However, these approaches fail to fully exploit the inherent tree structure of such sequences. To address these limitations and leverage established data properties, we propose Formation Tree-CLIP (FT-CLIP). This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks. We further introduce masking for to both character images and tree nodes, enabling efficient and effective training. This approach accelerates training significantly (by a factor of 2 or more) while enhancing accuracy. Extensive experiments show that processing characters through formation trees aligns better with their inherent properties than direct sequential methods, significantly enhancing the generality and usability of the representations.