Augmentation of Chinese Character Representations with Compositional Graph Learning (Student Abstract)

Authors

  • Jason Wang Harvard University
  • Kaiqun Fu South Dakota State University
  • Zhiqian Chen Mississippi State University
  • Chang-Tien Lu Virginia Tech

DOI:

https://doi.org/10.1609/aaai.v36i11.21674

Keywords:

Chinese Word Embedding, Natural Language Processing, Graph Representation Learning, Interpretability

Abstract

Chinese characters have semantic-rich compositional information in radical form. While almost all previous research has applied CNNs to extract this compositional information, our work utilizes deep graph learning on a compact, graph-based representation of Chinese characters. This allows us to exploit temporal information within the strict stroke order used in writing characters. Our results show that our stroke-based model has potential for helping large-scale language models on some Chinese natural language understanding tasks. In particular, we demonstrate that our graph model produces more interpretable embeddings shown through word subtraction analogies and character embedding visualizations.

Downloads

Published

2022-06-28

How to Cite

Wang, J., Fu, K., Chen, Z., & Lu, C.-T. (2022). Augmentation of Chinese Character Representations with Compositional Graph Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13075-13076. https://doi.org/10.1609/aaai.v36i11.21674