Thanks to visit codestin.com
Credit goes to github.com

Skip to content

ZaiLaGan is a Chinese spelling error corrector built on Line platform which can automatically detect or correct spelling errors in given Chinese texts such as message, email, and document.

Notifications You must be signed in to change notification settings

pj1114/ZaiLaGan

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ZaiLaGan - A chinese spelling error corrector

Team Members

  • Lawrence
  • Patrick
  • Sean
  • Erica

GPT2-Chinese Models

Name Introduction Author Google Drive Link
prose_pretrained Trained with 130 MB prose dataset collected from famous authors hughqiu Google Drive
prose_wiki_finetuned Finetune prose_pretrained with wikipedia dataset lawrence70726 Google Drive
prose_wiki_novel_finetuned Finetune prose_pretrained with wikipedia and novel datasets lawrence70726 Google Drive

Ngram Models

Name Introduction Author Google Drive Link
bigram bigram ericahuang0516 Google Drive
trigram trigram ericahuang0516 Google Drive
4gram 4gram ericahuang0516 Google Drive
5gram 5gram ericahuang0516 Google Drive

Word Substitution Models

Name Introduction Author Google Drive Link
word2vec.model Trained with chinese wiki corpus ericahuang0516 Google Drive
ckip CkipTagger contains WS, POS, NER models CKIP Lab Google Drive

About

ZaiLaGan is a Chinese spelling error corrector built on Line platform which can automatically detect or correct spelling errors in given Chinese texts such as message, email, and document.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.6%
  • Shell 0.4%