The following approaches are used to leverage monolingual data for low-resource NMT:
- back translation and forward translation
- joint training on both translation directions
- unsupervised NMT
- pre-training
- exploiting comparable corpus
- enhancing with bi-lingual dictionary 

Methods for Leveraging Mono-Lingual Data for Low-Resource NMT

In NMT, leveraging unlabeled monolingual data is relatively common since collecting monolingual data is much easier and of lower cost than parallel data.

Columbia University

The following data types have been leveraged to aid neural machine translation 
 for low-resource language pairs:
- monolingual data
- data from auxiliary languages 
- multi-modal data

Data Types Used to Help NMT for a Low-Resource Language Pair

Wang, R., Tan, X., Luo, R., Qin, T., & Liu, T.-Y. (8 2021). A Survey on Low-Resource Neural Machine Translation. Στο Z.-H. Zhou (Επιμ.), Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 (σσ. 4636–4643). doi:10.24963/ijcai.2021/629


Learn Before

Related

Learn After