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☆140Updated 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…☆188Updated last year
- A Benchmark for Classical Chinese Based on a Crowdsourcing System.☆60Updated 4 years ago
- ☆38Updated 2 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
- 《Spelling Error Correction with Soft-Masked BERT》论文复现☆36Updated 4 years ago
- 中文机器阅读理解数据集☆104Updated 4 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☆54Updated 2 years ago
- The official GitHub repository for AC-EVAL, an ancient Chinese evaluation suite for large language models (LLMs)☆14Updated 10 months ago
- a Corpus for Classical Chinese Language Event Extraction☆22Updated 2 years ago
- Yet Another Chinese Learner Corpus☆77Updated 3 years ago
- 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
- 基于prompt的中文文本分类。☆55Updated 2 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
- ☆418Updated last year
- text correction papers☆311Updated last year
- 非官方的MDCSpell论文的实现☆18Updated 2 years ago
- This is some summary code and model☆41Updated 3 years ago
- SIGHAN中文纠错数据集及转换后格式☆66Updated 5 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
- Implemention of NER model on chinese dataset.☆73Updated 2 years ago
- A PyTorch implementation of a BiLSTM \ BERT \ Roberta (+ BiLSTM + CRF) model for Chinese Word Segmentation (中文分词) .☆211Updated 3 years ago
- ☆29Updated 2 years ago
- 基于pytorch的中文拼写纠错,使用的模型是Bert以及SoftMaskedBert☆33Updated 3 years ago
- Source code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification☆535Updated 3 years ago
- SimCSE中文语义相似度对比学习模型☆88Updated 3 years ago
- ☆107Updated last year
- Ancient Chinese Corpus with Word Sense Annotation☆52Updated last year
- LERT: A Linguistically-motivated Pre-trained Language Model(语言学信息增强的预训练模型LERT)☆219Updated 2 months ago