CLApr 3, 2024

Low-resource neural machine translation with morphological modeling

arXiv:2404.02392v132 citationsh-index: 3NAACL-HLT
Originality Incremental advance
AI Analysis

This work addresses machine translation challenges for low-resource, morphologically-rich languages, offering incremental improvements over existing methods.

The paper tackled low-resource neural machine translation for morphologically-rich languages by proposing a framework with a two-tier transformer, multi-task training, and data augmentation, achieving competitive performance on Kinyarwanda-English translation compared to large multilingual models.

Morphological modeling in neural machine translation (NMT) is a promising approach to achieving open-vocabulary machine translation for morphologically-rich languages. However, existing methods such as sub-word tokenization and character-based models are limited to the surface forms of the words. In this work, we propose a framework-solution for modeling complex morphology in low-resource settings. A two-tier transformer architecture is chosen to encode morphological information at the inputs. At the target-side output, a multi-task multi-label training scheme coupled with a beam search-based decoder are found to improve machine translation performance. An attention augmentation scheme to the transformer model is proposed in a generic form to allow integration of pre-trained language models and also facilitate modeling of word order relationships between the source and target languages. Several data augmentation techniques are evaluated and shown to increase translation performance in low-resource settings. We evaluate our proposed solution on Kinyarwanda - English translation using public-domain parallel text. Our final models achieve competitive performance in relation to large multi-lingual models. We hope that our results will motivate more use of explicit morphological information and the proposed model and data augmentations in low-resource NMT.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes