Publication details

MUNI-NLP Systems for Low-resource Indic Machine Translation

Authors

SIGNORONI Edoardo RYCHLÝ Pavel

Year of publication 2023
Type Article in Proceedings
Conference Proceedings of the Eighth Conference on Machine Translation
MU Faculty or unit

Faculty of Informatics

Citation
web https://aclanthology.org/2023.wmt-1.91.pdf
Doi http://dx.doi.org/10.18653/v1/2023.wmt-1.91
Keywords low-resource;machine translation;NLP
Attached files
Description The WMT 2023 Shared Task on Low-Resource Indic Language Translation featured to and from Assamese, Khasi, Manipuri, Mizo on one side and English on the other. We submitted systems supervised neural machine translation systems for each pair and direction and experimented with different configurations and settings for both preprocessing and training. Even if most of them did not reach competitive performance, our experiments uncovered some interesting points for further investigation, namely the relation between dataset and model size, and the impact of the training framework. Moreover, the results of some of our preliminary experiments on the use of word embeddings initialization, backtranslation, and model depth were in contrast with previous work. The final results also show some disagreement in the automated metrics employed in the evaluation.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info