Improving Chinese Character Representation with Formation Tree
Hong, Yang, Li, Yinfei, Qiao, Xiaojun, Li, Rui, Zhang, Junsong
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Apr-19-2024
- Country:
- Asia (0.68)
- North America > United States
- Minnesota > Hennepin County > Minneapolis (0.14)
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Pattern Recognition (0.92)
- Natural Language (1.00)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence