cloudyskyy / Guwen-UNILMLinks
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。
☆50Updated 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☆142Updated 2 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…☆189Updated last year
- A Benchmark for Classical Chinese Based on a Crowdsourcing System.☆60Updated 4 years ago
- 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☆227Updated last year
- text correction papers☆311Updated last year
- Yet Another Chinese Learner Corpus☆77Updated 3 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
- 历届中文句法错误诊断技术评测数据集☆42Updated 3 years ago
- SIGHAN中文纠错数据集及转换后格式☆66Updated 5 years ago
- ☆419Updated 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☆54Updated 2 years ago
- 非官方的MDCSpell论文的实现☆18Updated 2 years ago
- ☆270Updated last year
- CCL 2020 中文隐喻识别与情感分析任务说明与数据集☆41Updated 4 years ago
- A Multi-modal Model Chinese Spell Checker Released on ACL2021.☆160Updated 2 years ago
- 全局指针统一处理嵌套与非嵌套NER的Pytorch实现☆402Updated 2 years ago
- ☆38Updated 2 years ago
- Source code for the paper "Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granular…☆41Updated 2 years ago
- 中文机器阅读理解数据集☆105Updated 4 years ago
- a Corpus for Classical Chinese Language Event Extraction☆22Updated 2 years ago
- A PyTorch implementation of a BiLSTM \ BERT \ Roberta (+ BiLSTM + CRF) model for Chinese Word Segmentation (中文分词) .☆213Updated 3 years ago
- 基于SpanBert的中文指代消解，pytorch实现☆101Updated 2 years ago
- MuCGEC中文纠错数据集及文本纠错SOTA模型开源；Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Gr…☆557Updated 2 years ago
- CCL 2022 汉语学习者文本纠错评测☆142Updated 2 years ago
- ☆107Updated last year
- Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021☆239Updated 3 years ago
- 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☆54Updated 2 years ago
- This is some summary code and model☆40Updated 3 years ago
- CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation☆492Updated 2 years ago
- 《Spelling Error Correction with Soft-Masked BERT》论文复现☆36Updated 4 years ago