Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Adaptive machine translation with large language models

Moslem, Yasmin orcid logoORCID: 0000-0003-4595-6877, Haque, Rejwanul orcid logoORCID: 0000-0003-1680-0099, Kelleher, John D. orcid logoORCID: 0000-0001-6462-3248 and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2023) Adaptive machine translation with large language models. In: 24th Annual Conference of the European Association for Machine Translation (EAMT 2023), 12-15 June 2023, Tampere, Finland.

Abstract
Consistency is a key requirement of highquality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domainspecific projects. Machine translation (MT) has achieved significant progress in the area of domain adaptation. However, real-time adaptation remains challenging. Large-scale language models (LLMs) have recently shown interesting capabilities of in-context learning, where they learn to replicate certain input-output text generation patterns, without further fine-tuning. By feeding an LLM at inference time with a prompt that consists of a list of translation pairs, it can then simulate the domain and style characteristics. This work aims to investigate how we can utilize in-context learning to improve real-time adaptive MT. Our extensive experiments show promising results at translation time. For example, LLMs can adapt to a set of in-domain sentence pairs and/or terminology while translating a new sentence. We observe that the translation quality with few-shot incontext learning can surpass that of strong encoder-decoder MT systems, especially for high-resource languages. Moreover, we investigate whether we can combine MT from strong encoder-decoder models with fuzzy matches, which can further improve translation quality, especially for less supported languages. We conduct our experiments across five diverse language pairs, namely English-to-Arabic (EN-AR), English-to-Chinese (EN-ZH), English-toFrench (EN-FR), English-to-Kinyarwanda (EN-RW), and English-to-Spanish (EN-ES).
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of 24th Annual Conference of the European Association for Machine Translation (EAMT 2023. . European Association for Machine Translation (EAMT).
Publisher:European Association for Machine Translation (EAMT)
Official URL:https://aclanthology.org/2023.eamt-1.22/
Copyright Information:© 2023 The Authors.
Funders:Science Foundation Ireland (SFI) Centre for Research Training in Digitally-Enhanced Reality (d-real) under Grant No. 18/CRT/6224, Science Foundation Ireland 9SFI) Grant No. 13/RC/2106 P2, Microsoft Research
ID Code:28326
Deposited On:02 Jun 2023 13:44 by Thomas Murtagh . Last Modified 22 Sep 2023 09:52
Documents

Full text available as:

[thumbnail of 2301.13294.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0
437kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record