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 …

Mt2: Towards a multi-task machine translation model with translation-specific in-context learning

C Li, M Liu, H Zhang, Y Chen, J Xu… - Proceedings of the 2023 …, 2023 - aclanthology.org
Sentence-level translation, document-level translation, translation memory, and terminology
constrained translation play an important role in machine translation. Most of the previous …

Translating a low-resource language using GPT-3 and a human-readable dictionary

M Elsner, J Needle - … of the 20th SIGMORPHON workshop on …, 2023 - aclanthology.org
We investigate how well words in the polysynthetic language Inuktitut can be translated by
combining dictionary definitions, without use of a neural machine translation model trained …

Controlling styles in neural machine translation with activation prompt

Y Wang, Z Sun, S Cheng, W Zheng, M Wang - arXiv preprint arXiv …, 2022 - arxiv.org
Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is
crucial for enhancing user experience. Earlier studies on this topic typically concentrate on …

Unified model learning for various neural machine translation

Y Liang, F Meng, J Xu, J Wang, Y Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Existing neural machine translation (NMT) studies mainly focus on developing dataset-
specific models based on data from different tasks (eg, document translation and chat …

GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning

R Ramos, EA Chimoto, M ter Hoeve… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce GrammaMT, a grammatically-aware prompting approach for machine
translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description …

Improving In-context Machine Translation

S Sia - 2023 - jscholarship.library.jhu.edu
Abstract In-context Learning for Machine Translation (MT) is a new paradigm enabled by
very large language models self-supervised on massive amounts of language data. These …