Improving Chinese Character Representation with Formation Tree

arXiv:2404.12693v1 Announce Type: cross
Abstract: 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 …

abstract arxiv challenges characters chinese continuous cs.cv cs.lg growth improving prior representation research space sparsity tree type unique usage vast