Benchmarking Azerbaijani Neural Machine Translation
Computation and Language
2022-08-01 v1
Abstract
Little research has been done on Neural Machine Translation (NMT) for Azerbaijani. In this paper, we benchmark the performance of Azerbaijani-English NMT systems on a range of techniques and datasets. We evaluate which segmentation techniques work best on Azerbaijani translation and benchmark the performance of Azerbaijani NMT models across several domains of text. Our results show that while Unigram segmentation improves NMT performance and Azerbaijani translation models scale better with dataset quality than quantity, cross-domain generalization remains a challenge
Cite
@article{arxiv.2207.14473,
title = {Benchmarking Azerbaijani Neural Machine Translation},
author = {Chih-Chen Chen and William Chen},
journal= {arXiv preprint arXiv:2207.14473},
year = {2022}
}
Comments
Published in The International Conference and Workshop on Agglutinative Language Technologies as a Challenge for NLP (ALTNLP) https://www.altnlp.org