Applied Sciences Manuscript ID: applsci-1927936 (https://www.mdpi.com/journal/applsci)

Research on Traditional Mongolian-Chinese Neural Machine Translation Based on Dependency Syntactic Information and Transformer

Experiment scripts and related files contains experiment scripts and results. In view of the excessive size of the experiment results, they have been stored on a network drive, and the sharing links are provided. On github, you can download the pre-trained model (035_ckpt.tar https://github.com/CK-IMUT-501/applsci-1927936/tree/master) saved when the improved model "Transformer_Enc_Dec_Imp + Syn + EZ (Both)" was trained with a random seed of 6421.

dep_process contains scripts for processing dependent syntactic information.

As the dataset is private, only a few example sentences can be given for testing purposes.