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。
☆41Updated 2 years ago
Related projects: ⓘ
- A Benchmark for Classical Chinese Based on a Crowdsourcing System.☆49Updated 3 years ago
- 基于pytorch的中文拼写纠错，使用的模型是Bert以及SoftMaskedBert☆30Updated 2 years ago
- ☆27Updated last year
- SikuBERT：四库全书的预训练语言模型（四库BERT） Pre-training Model of Siku Quanshu☆110Updated 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…☆146Updated 9 months ago
- 非官方的MDCSpell论文的实现☆17Updated last year
- 古文语言理解测评基准 Classical Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard☆45Updated last year
- Dynamic Connected Networks for Chinese Spelling Check☆49Updated 5 months ago
- ChineseBert用于中文拼写纠错☆39Updated last year
- CCL2022汉语学习者文本纠错评测任务赛道二——CGED-8第一名解决方案☆52Updated last year
- ☆18Updated last year
- Yet Another Chinese Learner Corpus☆71Updated 2 years ago
- ☆29Updated this week
- 复现 Soft-Masked BERT， 论文 Spelling Error Correction with Soft-Masked BERT☆12Updated 3 years ago
- 开源QG系统(Question Generation,问题生成)，基于Pytorch和Transformer编写☆54Updated last month
- 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP☆24Updated 5 years ago
- 基于prompt的中文文本分类。☆53Updated last year
- 一个面向繁体中文古籍分词的python工具包☆31Updated 2 years ago
- Code & data for our EMNLP2022 paper "SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser"☆79Updated 6 months ago
- This is some summary code and model☆38Updated 2 years ago
- Finetune t5 and bart on Chinese Grammatical Error Correction data.☆14Updated 2 years ago
- SIGHAN中文纠错数据集及转换后格式☆62Updated 4 years ago
- 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☆56Updated last year
- Source code for the paper "Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granular…☆37Updated last year
- 《Spelling Error Correction with Soft-Masked BERT》论文复现☆32Updated 3 years ago
- 历届中文句法错误诊断技术评测数据集☆33Updated 2 years ago
- 基于SpanBert的中文指代消解，pytorch实现☆95Updated last year
- ☆126Updated last year
- Code for ACL 2021 paper. MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition.☆67Updated 2 years ago
- GPLinker_pytorch☆75Updated 2 years ago