Sikubert
A pre-trained language model specifically designed for automatic processing of ancient texts, based on the BERT architecture and trained using high-quality corpus from 'Siku Quanshu'
Downloads 1,900
Release Time : 3/2/2022
Model Overview
A pre-trained language model for intelligent processing tasks of ancient Chinese, supporting natural language processing of classical Chinese and ancient Chinese
Model Features
Specialized for Ancient Texts
A pre-trained model specifically optimized for ancient Chinese and classical Chinese
High-Quality Corpus
Uses the authoritative 'Siku Quanshu' full text as training corpus
Dual Architecture Support
Provides pre-trained models with both BERT and RoBERTa architectures
Model Capabilities
Classical Chinese Understanding
Ancient Text Mining
Ancient Chinese Information Processing
Use Cases
Digital Humanities Research
Ancient Text Analysis
Automatic analysis and information extraction of ancient documents
Historical Document Processing
Processing and analyzing various historical documents
Educational Research
Ancient Chinese Teaching Assistance
Assisting in the teaching and research of ancient Chinese and classical Chinese
Featured Recommended AI Models
Š 2025AIbase