https://github.com/madrugado/language-identification

Few models for language identification and code switching tasks
https://github.com/madrugado/language-identification

Last synced: about 2 months ago
JSON representation

Few models for language identification and code switching tasks

• Host: GitHub
• URL: https://github.com/madrugado/language-identification
• Owner: madrugado
• Created: 2019-07-08T13:14:49.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-05-03T19:47:08.000Z (8 months ago)
• Last Synced: 2024-05-03T21:00:48.081Z (8 months ago)
• Language: Python
• Size: 1.84 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
This is my tryout for language identification.

### Problems

1. There are three languages: Spanish (ES), Portuguese (PT-PT) and English (EN) which need to be identified given a sentence.

2. There are two language variants: European Portuguese (PT-PT) and Brazilian Portuguese (PT-BR), they should be tell apart given a sentence.

3. There are tweets written English and Spanish. Each token in a tweet should be identified to belong to 'en', 'es' or 'other' class.

There are additional info for problems 1 and 2 in [readme](./langid/README.md) under langid folder, and about the third problem in  [readme](./code-switching/README.md) under code-switching folder.