BIRD: Bronze Inscription Restoration and Dating

Wenjie Hua; Hoang H Nguyen; Gangyan Ge

EMNLP 20250 citations

BIRD: Bronze Inscription Restoration and Dating

Abstract

Bronze inscriptions from early China are fragmentary and difficult to date. We introduce BIRD (Bronze Inscription Restoration and Dating), a fully encoded dataset grounded in standard scholarly transcriptions and chronological labels. We further propose an allograph-aware masked language modeling framework that integrates domain- and task-adaptive pretraining with a Glyph Net (GN), which links graphemes and allographs. Experiments show that GN improves restoration, while glyph-biased sampling yields gains in dating.

BibTeX

@inproceedings{emnlp2025_birdbronzeinscri,
  title = {BIRD: Bronze Inscription Restoration and Dating},
  author = {Wenjie Hua and Hoang H Nguyen and Gangyan Ge},
  booktitle = {EMNLP 2025},
  year = {2025}
}