hsc748NLP / SikuGPT
☆16Updated last year
Alternatives and similar repositories for SikuGPT:
Users that are interested in SikuGPT are comparing it to the libraries listed below
- 古文语言理解测评基准 Classical Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard☆47Updated last year
- Tokenizer POS-tagger and Dependency-parser for Classical Chinese☆14Updated 2 months ago
- 一个面向繁体中文古籍分词的python工具包☆31Updated 3 years ago
- SikuBERT:四库全书的预训练语言模型(四库BERT) Pre-training Model of Siku Quanshu☆119Updated last year
- An evaluation bentchmark for classical Chinese☆12Updated last year
- Evaluation of Natural Language Processing (NLP) tools for the Ancient Chinese language☆34Updated 2 weeks ago
- <u><a href="https://circse.github.io/LT4HALA/" style="color: white">Workshop on Language Technologies for Historical and Ancient Language…☆33Updated 8 months ago
- CCL 2023 古汉语通假字语料库的构建及应用研究:通假字资源库☆12Updated last year
- ☆32Updated last year
- GuwenModels: 古文自然语言处理模型合集, 收录互联网上的古文相关模型及资源. A collection of Classical Chinese natural language processing models, including Classical Ch…☆165Updated last year
- ☆24Updated last year
- 古文现代文翻译平行语料库☆100Updated 3 years ago
- ☆36Updated 2 years ago
- Tokenizer POS-tagger and Dependency-parser for Classical Chinese☆64Updated 2 months ago
- <数字人文教程>资源合集☆89Updated 8 months ago
- [ACL'24] Moral Emotion Dataset & Classifier☆13Updated 5 months ago
- AnchiBERT: A Pre-Trained Model for Ancient Chinese Language Understanding and Generation(古文预训练模型)☆63Updated 3 years ago
- Ancient Chinese Corpus with Word Sense Annotation☆46Updated 8 months ago
- A Benchmark for Classical Chinese Based on a Crowdsourcing System.☆54Updated 3 years ago
- ☆273Updated 2 months ago
- 渊 - A project for Classical Chinese☆95Updated 2 years ago
- Tokenizer POS-tagger and Dependency-parser for Classical Chinese☆13Updated last year
- BERT-CCPoem is an BERT-based pre-trained model particularly for Chinese classical poetry☆147Updated 2 years ago
- ☆28Updated 2 months ago
- ☆17Updated last year
- ☆15Updated last year
- 本仓库是基于bert4keras实现的古文-现代文翻译模型。具体使用了基于掩码自注意力机制的UNILM(Li al., 2019)预训练模型作为翻译系统的backbone。我们首先使用了普通的中文(现代文)BERT、Roberta权重作为UNILM的初始权重以训练UNILM…☆45Updated 2 years ago
- Yet Another Chinese Learner Corpus☆76Updated 3 years ago
- Hanja Understanding Evaluation Dataset☆13Updated 2 years ago
- Automated Essay Scoring Method for Chinese Second Language Writing☆25Updated 2 years ago