Continual lifelong learning in natural language processing: A survey

M Biesialska, K Biesialska, MR Costa-Jussa - arxiv preprint arxiv …, 2020‏ - arxiv.org
Continual learning (CL) aims to enable information systems to learn from a continuous data
stream across time. However, it is difficult for existing deep learning architectures to learn a …

Adaptive machine translation with large language models

Y Moslem, R Haque, JD Kelleher, A Way - arxiv preprint arxiv:2301.13294, 2023‏ - arxiv.org
Consistency is a key requirement of high-quality translation. It is especially important to
adhere to pre-approved terminology and adapt to corrected translations in domain-specific …

Simple, scalable adaptation for neural machine translation

A Bapna, N Arivazhagan, O Firat - arxiv preprint arxiv:1909.08478, 2019‏ - arxiv.org
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach
for adapting to new languages and domains. However, fine-tuning requires adapting and …

Unsupervised domain clusters in pretrained language models

R Aharoni, Y Goldberg - arxiv preprint arxiv:2004.02105, 2020‏ - arxiv.org
The notion of" in-domain data" in NLP is often over-simplistic and vague, as textual data
varies in many nuanced linguistic aspects such as topic, style or level of formality. In …

A survey of domain adaptation for machine translation

C Chu, R Wang - Journal of information processing, 2020‏ - jstage.jst.go.jp
Neural machine translation (NMT) is a deep learning based approach for machine
translation, which outperforms traditional statistical machine translation (SMT) and yields the …

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 …

Reducing gender bias in neural machine translation as a domain adaptation problem

D Saunders, B Byrne - arxiv preprint arxiv:2004.04498, 2020‏ - arxiv.org
Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to
women than to men. In Neural Machine Translation (NMT) gender bias has been shown to …

Boosting neural machine translation with similar translations

J Xu, JM Crego, J Senellart - Annual Meeting of the Association for …, 2020‏ - hal.science
This paper explores data augmentation methods for training Neural Machine Translation to
make use of similar translations, in a comparable way a human translator employs fuzzy …

Guiding neural machine translation with retrieved translation pieces

J Zhang, M Utiyama, E Sumita, G Neubig… - arxiv preprint arxiv …, 2018‏ - arxiv.org
One of the difficulties of neural machine translation (NMT) is the recall and appropriate
translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and …

The practical ethics of bias reduction in machine translation: Why domain adaptation is better than data debiasing

M Tomalin, B Byrne, S Concannon, D Saunders… - Ethics and Information …, 2021‏ - Springer
This article probes the practical ethical implications of AI system design by reconsidering the
important topic of bias in the datasets used to train autonomous intelligent systems. The …