cloudyskyy / Guwen-UNILM
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模型（具体在文中分别为B-UNILM以及R-UNILM）。为了更好的使UNILM模型适应古文的特性，我们尝试使用了在古文预训练模型Guwen-BERT，作为UNILM的初始权重，并且获得了最优的效果。
☆49Updated 3 years ago
Alternatives and similar repositories for Guwen-UNILM
Users that are interested in Guwen-UNILM are comparing it to the libraries listed below
Sorting:
- SikuBERT：四库全书的预训练语言模型（四库BERT） Pre-training Model of Siku Quanshu☆129Updated last year
- A Benchmark for Classical Chinese Based on a Crowdsourcing System.☆58Updated 3 years ago
- ☆35Updated 2 years ago
- 古文语言理解测评基准 Classical Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard☆50Updated last year
- 文言文命名实体识别，基于BILSTM+CRF完成文言文的命名实体实体，识别实体包括人物、地点、机构、时间等。☆9Updated 4 years ago
- 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…☆175Updated last year
- 非官方的MDCSpell论文的实现☆18Updated 2 years ago
- a Corpus for Classical Chinese Language Event Extraction☆21Updated last year
- Yet Another Chinese Learner Corpus☆77Updated 3 years ago
- Ancient Chinese Corpus with Word Sense Annotation☆47Updated 11 months ago
- 一个面向繁体中文古籍分词的python工具包☆32Updated 3 years ago
- 基于pytorch的中文拼写纠错，使用的模型是Bert以及SoftMaskedBert☆32Updated 3 years ago
- 古文现代文翻译平行语料库☆104Updated 3 years ago
- CCL 2022 汉语学习者文本纠错评测☆141Updated 2 years ago
- ☆27Updated last year
- This repository is intended for people who are interesting in learning/reading Classical Chinese (文言文) but be at a loss what to do to. As…☆13Updated 3 years ago
- SIGHAN中文纠错数据集及转换后格式☆64Updated 5 years ago
- 文言文翻译、古文翻译 语料数 据集☆50Updated 4 years ago
- 基于SpanBert的中文指代消解，pytorch实现☆97Updated 2 years ago
- CCL 2020 中文隐喻识别与情感分析任务说明与数据集☆39Updated 4 years ago
- 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP☆24Updated 6 years ago
- 《Spelling Error Correction with Soft-Masked BERT》论文复现☆32Updated 3 years ago
- The official GitHub repository for AC-EVAL, an ancient Chinese evaluation suite for large language models (LLMs)☆13Updated 6 months ago
- Source code for the paper "Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granular…☆41Updated last year
- 基于GOOGLE T5中文生成式模型的摘要生成/指代消解，支持batch批量生成，多进程☆222Updated last year
- 基于Pytorch+BERT+CRF的NLP序列标注模型，目前包括分词，词性标注，命名实体识别等☆60Updated 2 years ago
- This is some summary code and model☆40Updated 3 years ago
- CMeEE/CBLUE/NER实体识别☆129Updated 3 years ago
- Finetune t5 and bart on Chinese Grammatical Error Correction data.☆18Updated 2 years ago
- 基于prompt的中文文本分类。☆55Updated 2 years ago