Adaptive Machine Translation with Large Language Models

01/30/2023
by   Yasmin Moslem, et al.
0

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and corrected translations in domain-specific 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 with a prompt that consists of a list of translation pairs, it can then simulate the domain and style characteristics at inference time. 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, GPT-3.5 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 in-context 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 the translation, especially for less supported languages. We conduct our experiments across five diverse languages, namely English-to-Arabic (EN-AR), English-to-Chinese (EN-ZH), English-to-French (EN-FR), English-to-Kinyarwanda (EN-RW), and English-to-Spanish (EN-ES) language pairs.

READ FULL TEXT

page 1

page 4

page 5

page 7

research
08/11/2022

Domain-Specific Text Generation for Machine Translation

Preservation of domain knowledge from the source to target is crucial in...
research
10/23/2021

PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation

We introduce a high-quality and large-scale Vietnamese-English parallel ...
research
08/19/2021

Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021

This paper reports the Machine Translation (MT) systems submitted by the...
research
01/05/2021

Local Translation Services for Neglected Languages

Taking advantage of computationally lightweight, but high-quality transl...
research
05/09/2022

CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality

The machine translation (MT) task is typically formulated as that of ret...
research
10/10/2022

Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions

We explore zero-shot adaptation, where a general-domain model has access...
research
09/20/2022

Vega-MT: The JD Explore Academy Translation System for WMT22

We describe the JD Explore Academy's submission of the WMT 2022 shared g...

Please sign up or login with your details

Forgot password? Click here to reset