BriefGPT.xyz
Jul, 2024
利用RNN提升数字化科普蒂克手稿中的文本补全方法
Lacuna Language Learning: Leveraging RNNs for Ranked Text Completion in Digitized Coptic Manuscripts
HTML
PDF
Lauren Levine, Cindy Tung Li, Lydia Bremer-McCollum, Nicholas Wagner, Amir Zeldes
TL;DR
本论文介绍了一种用于预测古老手稿中科普特文字符的双向RNN模型，尽管在恢复文字缺失的过程中准确率下降，但能够帮助学者对Coptic手稿的文字重建进行排名，从而增强传统的文本恢复方法。
Abstract
ancient manuscripts
are frequently damaged, containing gaps in the text known as
lacunae
. In this paper, we present a
bidirectional rnn model
→