tongchangD / bert_for_correctorLinks
基于bert进行中文文本纠错
☆237Updated 2 years ago
Alternatives and similar repositories for bert_for_corrector
Users that are interested in bert_for_corrector are comparing it to the libraries listed below
Sorting:
- SpellGCN☆253Updated 4 years ago
- ☆86Updated 4 years ago
- 李傲龍的博客☆82Updated last year
- 🙈 An unofficial implementation of SoftMaskedBert based on huggingface/transformers.☆96Updated 4 years ago
- Unilm for Chinese Chitchat Robot.基于Unilm模型的夸夸式闲聊机器人项目。☆158Updated 4 years ago
- Code for chinese error detection module, using n-gram and bi-lstm☆135Updated 6 years ago
- Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021☆238Updated 3 years ago
- 中文文本纠错模型,keras实现☆75Updated 4 years ago
- 汉字字符特征提取工具,可以提取出字符中的字音(声母、韵母、声调)、字形(偏旁、部首)、四角编码等特征,同时可作为tensor输入到模型☆137Updated 5 years ago
- Modify Chinese text, modified on LaserTagger Model. 文本复述,基于lasertagger做中文文本数据增强。☆322Updated last year
- PyTorch impelementations of BERT-based Spelling Error Correction Models. 基于BERT的文本纠错模型,使用PyTorch实现。☆273Updated 6 months ago
- ☆102Updated 4 years ago
- 中文版unilm预训练模型☆83Updated 4 years ago
- Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained La…☆431Updated 5 years ago
- 使用bert做领域分类、意图识别和槽位填充任务☆77Updated 5 years ago
- Modify Chinese text, modified on LaserTagger Model. I name it "文本手术刀".目前,本项目实现了一个文本复述任务,用于NLP语料的数据增强。☆214Updated 2 years ago
- This repository is for the paper "A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check"☆295Updated 5 years ago
- implementation several deep text match (text similarly) models for keras . cdssm, arc-ii,match_pyramid, mvlstm ,esim, drcn ,bimpm, bert, …☆291Updated 4 years ago
- 真 · “Deep Learning for Humans”☆142Updated 3 years ago
- 中文NLP数据集☆158Updated 6 years ago
- pytorch中文语言模型预训练☆390Updated 5 years ago
- Chinese Language Generation Evaluation 中文生成任务基准测评☆248Updated 4 years ago
- NER(命名实体识别)中文语料,一站式获取☆131Updated 5 years ago
- 中文纠错☆93Updated 3 years ago
- ☆129Updated 2 years ago
- 微调预训练语言模型,解决多标签分类任务(可加载BERT、Roberta、Bert-wwm以及albert等知名开源tf格式的模型)☆141Updated 5 years ago
- 整理一下在keras中使用T5模型的要点☆173Updated 3 years ago
- ChineseTextualInference project including chinese corpus build and inferecence model, 中文文本推断项目,包括88万文本蕴含中文文本蕴含数据集的翻译与构建,基于深度学习的文本蕴含判定模型构建…☆174Updated 6 years ago
- Self complemented Pinyin2Chinese demo use algorithms including Trie and HMM model , 基于隐马尔科夫模型与Trie树的拼音切分与拼音转中文的简单demo实现。☆86Updated 7 years ago
- Bert预训练模型fine-tune计算文本相似度☆107Updated 2 years ago