用AI修复和断代古代青铜铭文，提升古文字研究效率
BIRD: Bronze Inscription Restoration and Dating
- 构建含标准转写与年代标签的完整数据集
- 图符网络使铭文修复准确率显著提升
- 适配异体字的采样策略改善断代精度
早期中国青铜铭文残缺且难断代。我们提出BIRD（青铜铭文修复与断代）——一个基于标准学术转写和年代标签的全编码数据集。同时设计了一种兼顾异体字的掩码语言建模框架，结合领域与任务自适应预训练，引入图符网络（Glyph Net, GN），建立字形与异体字间的关联。实验表明，图符网络有效提升修复效果，而以字形为偏倚的采样策略显著改善断代性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。