A survey of multilingual neural machine translation

R Dabre, C Chu, A Kunchukuttan - ACM Computing Surveys (CSUR), 2020‏ - dl.acm.org
We present a survey on multilingual neural machine translation (MNMT), which has gained
a lot of traction in recent years. MNMT has been useful in improving translation quality as a …

Survey of low-resource machine translation

B Haddow, R Bawden, AVM Barone, J Helcl… - Computational …, 2022‏ - direct.mit.edu
We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

Domain adaptation and multi-domain adaptation for neural machine translation: A survey

D Saunders - Journal of Artificial Intelligence Research, 2022‏ - jair.org
The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

Chain-of-dictionary prompting elicits translation in large language models

H Lu, H Yang, H Huang, D Zhang, W Lam… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large language models (LLMs) have shown surprisingly good performance in multilingual
neural machine translation (MNMT) even when trained without parallel data. Yet, despite the …

Dictionary-based phrase-level prompting of large language models for machine translation

M Ghazvininejad, H Gonen, L Zettlemoyer - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities
via prompting, even though they were not explicitly trained for this task. However, even given …

Measuring and mitigating name biases in neural machine translation

J Wang, B Rubinstein, T Cohn - … of the 60th Annual Meeting of the …, 2022‏ - aclanthology.org
Abstract Neural Machine Translation (NMT) systems exhibit problematic biases, such as
stereotypical gender bias in the translation of occupation terms into languages with …

Lexically constrained neural machine translation with Levenshtein transformer

RH Susanto, S Chollampatt, L Tan - arxiv preprint arxiv:2004.12681, 2020‏ - arxiv.org
This paper proposes a simple and effective algorithm for incorporating lexical constraints in
neural machine translation. Previous work either required re-training existing models with …

CSP: code-switching pre-training for neural machine translation

Z Yang, B Hu, A Han, S Huang, Q Ju - Proceedings of the 2020 …, 2020‏ - aclanthology.org
This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP
for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which …

[PDF][PDF] Lexical-constraint-aware neural machine translation via data augmentation

G Chen, Y Chen, Y Wang, VOK Li - Proceedings of the Twenty-Ninth …, 2021‏ - ijcai.org
Leveraging lexical constraint is extremely significant in domain-specific machine translation
and interactive machine translation. Previous studies mainly focus on extending beam …

EDITOR: An edit-based transformer with repositioning for neural machine translation with soft lexical constraints

W Xu, M Carpuat - Transactions of the Association for Computational …, 2021‏ - direct.mit.edu
We introduce an Edi t-Based T ransf O rmer with R epositioning (EDITOR), which makes
sequence generation flexible by seamlessly allowing users to specify preferences in output …