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 …

Occupational biases in Norwegian and multilingual language models

S Touileb, L Øvrelid, E Velldal - … of the 4th Workshop on Gender …, 2022 - aclanthology.org
In this paper we explore how a demographic distribution of occupations, along gender
dimensions, is reflected in pre-trained language models. We give a descriptive assessment …

Findings of the WMT 2020 biomedical translation shared task: Basque, Italian and Russian as new additional languages

R Bawden, GM Di Nunzio, C Grozea… - Fifth Conference on …, 2020 - research.ed.ac.uk
Abstract Machine translation of scientific abstracts and terminologies has the potential to
support health professionals and biomedical researchers in some of their activities. In the …

Measuring harmful representations in Scandinavian language models

S Touileb, D Nozza - arxiv preprint arxiv:2211.11678, 2022 - arxiv.org
Scandinavian countries are perceived as role-models when it comes to gender equality.
With the advent of pre-trained language models and their widespread usage, we investigate …

Improving automated program repair with domain adaptation

A Zirak, H Hemmati - ACM Transactions on Software Engineering and …, 2024 - dl.acm.org
Automated Program Repair (APR) is defined as the process of fixing a bug/defect in the
source code, by an automated tool. APR tools have recently experienced promising results …

Domain adaptation for neural machine translation

D Saunders - 2021 - repository.cam.ac.uk
The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

[HTML][HTML] Learning Horn envelopes via queries from language models

S Blum, R Koudijs, A Ozaki, S Touileb - International Journal of …, 2024 - Elsevier
We present an approach for systematically probing a trained neural network to extract a
symbolic abstraction of it, represented as a Boolean formula. We formulate this task within …

Exploring the effects of negation and grammatical tense on bias probes

S Touileb - Proceedings of the 2nd Conference of the Asia-Pacific …, 2022 - aclanthology.org
We investigate in this paper how correlations between occupations and gendered-pronouns
can be affected and changed by adding negation in bias probes, or changing the …

Domain adapted machine translation: What does catastrophic forgetting forget and why?

D Saunders, S DeNeefe - arxiv preprint arxiv:2412.17537, 2024 - arxiv.org
Neural Machine Translation (NMT) models can be specialized by domain adaptation, often
involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid …

Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation

K Chen, D Zhuang, M Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Neural Machine Translation (NMT) models have achieved comparable results to human
translation with a large number of parallel corpora available. However, their performance …