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 …
(NMT) models to become extremely powerful, given sufficient training data and training time …
Occupational biases in Norwegian and multilingual language models
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 …
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
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 …
support health professionals and biomedical researchers in some of their activities. In the …
Measuring harmful representations in Scandinavian language models
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 …
With the advent of pre-trained language models and their widespread usage, we investigate …
Improving automated program repair with domain adaptation
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 …
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 …
(NMT) models to become extremely powerful, given sufficient training data and training time …
[HTML][HTML] Learning Horn envelopes via queries from language models
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 …
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 …
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?
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 …
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
Neural Machine Translation (NMT) models have achieved comparable results to human
translation with a large number of parallel corpora available. However, their performance …
translation with a large number of parallel corpora available. However, their performance …