liwenju0 / error_text_gen
用于生成文本纠错模型(如Gector)需要的大量数据。
☆14Updated last year
Related projects ⓘ
Alternatives and complementary repositories for error_text_gen
- pytorch版基于gpt+nezha的中文多轮Cdial☆11Updated 2 years ago
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- source code of EMNLP2021: A Lightweight Pretrained Model for Chinese Spelling Check☆14Updated 3 years ago
- ☆24Updated 4 years ago
- ☆10Updated 2 years ago
- Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"☆29Updated last year
- ☆32Updated 3 years ago
- Chinese Grammatical Error Diagnosis☆11Updated 3 years ago
- 无监督文本生成的一些方法☆49Updated 3 years ago
- 有一个通用实体关系事件抽取的任务，需要使用到UIE模框架，而且需要将起部署到昇腾310服务器上，因为UIE模型底层使用的是ernie3.0，但是目前paddle官方还不支持ernie3.0模型在昇腾310上部署，所以才有了以下的操作，主要过程是，先试用paddle训练处模型…☆17Updated 2 years ago
- Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation☆22Updated 4 years ago
- ☆20Updated 4 years ago
- huggingface ChineseBert Tokenizer☆15Updated 2 years ago
- TensorRT☆11Updated 4 years ago
- 格物-多语言和中文大规模预训练模型-轻量版，涵盖纯中文、知识增强、113个语种多语言，采用主流Roberta架构，适用于NLU和NLG任务， 支持pytorch、tensorflow、uer、huggingface等框架。 Multilingual and Chinese …☆26Updated 2 years ago
- CTC2021-中文文本纠错大赛的SOTA方案及在线演示☆72Updated last year
- ROUGE for multilingual Summarization☆23Updated 3 years ago
- pytorch版bert权重转tf☆21Updated 4 years ago
- 根据维基百科历史编辑数据提取纠错语料。☆12Updated 2 years ago
- 针对NER领域提供从线下训练到线上部署的一整套闭环流程☆12Updated 3 years ago
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆46Updated last year
- ☆10Updated 2 years ago
- 分享一些S2S在实际应用中遇到的问题和解决方法。☆27Updated 4 years ago
- Unsupervised tableQA and databaseQA on chinese finance question and tabular data☆12Updated last year
- using lear to do ner extraction☆29Updated 2 years ago
- A Pytorch implementation for "Hierarchical Attention Network with Pairwise Loss for Chinese Zero Pronoun Resolution“ (AAAI 2020).☆9Updated 3 years ago
- 中文AllenNLP教程（持续更新）☆14Updated 5 years ago