Improving Chinese Character Representation with Formation Tree
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909175718608896 |
|---|---|
| author | Hong, Yang Li, Yinfei Qiao, Xiaojun Li, Rui Zhang, Junsong |
| author_facet | Hong, Yang Li, Yinfei Qiao, Xiaojun Li, Rui Zhang, Junsong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12693 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Chinese Character Representation with Formation Tree Hong, Yang Li, Yinfei Qiao, Xiaojun Li, Rui Zhang, Junsong Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Improving Chinese Character Representation with Formation Tree |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.12693 |