Saved in:
Bibliographic Details
Main Authors: Hua, Wenjie, Nguyen, Hoang H., Ge, Gangyan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.01589
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914132765179904
author Hua, Wenjie
Nguyen, Hoang H.
Ge, Gangyan
author_facet Hua, Wenjie
Nguyen, Hoang H.
Ge, Gangyan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BIRD: Bronze Inscription Restoration and Dating
Hua, Wenjie
Nguyen, Hoang H.
Ge, Gangyan
Computation and Language
I.2.7
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.
title BIRD: Bronze Inscription Restoration and Dating
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2511.01589