Skip to content

This project is an improved version of the official Seq2Seq tutorial of PyTorch, featuring a Chinese-English machine translator (GRU + Bahdanau Attention)

License

Notifications You must be signed in to change notification settings

JSLEE-0703/Seq2seq-Translator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Seq2seq-Translator

Author: YUTONG LI (Harry)
GitHub: https://github.com/JSLEE-0703/Seq2seq-Translator

English-to-Chinese neural machine translation with attention implemented in PyTorch. Uses jieba for Chinese word segmentation.

Note

cleaner.py is used to remove irregular characters from datasets. For example, some datasets may contain contributor information in each line, which can be cleaned using cleaner.py.

Install

pip install torch torchvision jieba matplotlib

Result

image image image image

Conclusion

This project already has a quite complete framework. Currently, due to the simplicity of the data set, there are problems with the translation of long and complex sentences as well as some unfamiliar word combinations. If you want to further improve the translation effect, please use a higher-quality data set. If you have any suggestions for improvement, please contact me.

About

This project is an improved version of the official Seq2Seq tutorial of PyTorch, featuring a Chinese-English machine translator (GRU + Bahdanau Attention)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published