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 …
The paradox of the compositionality of natural language: A neural machine translation case study
Obtaining human-like performance in NLP is often argued to require compositional
generalisation. Whether neural networks exhibit this ability is usually studied by training …
generalisation. Whether neural networks exhibit this ability is usually studied by training …
On compositional generalization of neural machine translation
Modern neural machine translation (NMT) models have achieved competitive performance
in standard benchmarks such as WMT. However, there still exist significant issues such as …
in standard benchmarks such as WMT. However, there still exist significant issues such as …
Categorizing semantic representations for neural machine translation
Modern neural machine translation (NMT) models have achieved competitive performance
in standard benchmarks. However, they have recently been shown to suffer limitation in …
in standard benchmarks. However, they have recently been shown to suffer limitation in …
How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts
Neural Machine Translation systems built on top of Transformer-based architectures are
routinely improving the state-of-the-art in translation quality according to word-overlap …
routinely improving the state-of-the-art in translation quality according to word-overlap …
[PDF][PDF] Integrating professional machine translation literacy and data literacy
R Krüger - Lebende Sprachen, 2022 - degruyter.com
The data-driven paradigm of neural machine translation is a powerful translation technology
based on state-of-the art approaches in artificial intelligence research. This technology is …
based on state-of-the art approaches in artificial intelligence research. This technology is …
Systematicity, compositionality and transitivity of deep NLP models: a metamorphic testing perspective
Metamorphic testing has recently been used to check the safety of neural NLP models. Its
main advantage is that it does not rely on a ground truth to generate test cases. However …
main advantage is that it does not rely on a ground truth to generate test cases. However …
[图书][B] Exploring the implications of complexity thinking for translation studies
K Marais, R Meylaerts - 2022 - api.taylorfrancis.com
Complexity theory, complexity philosophy or complexity thinking, whichever way one wants
to look at the development of complexity in scholarly thinking, is suggesting a foundational …
to look at the development of complexity in scholarly thinking, is suggesting a foundational …
Joint Dropout: Improving Generalizability in Low-Resource Neural Machine Translation through Phrase Pair Variables
Despite the tremendous success of Neural Machine Translation (NMT), its performance on
low-resource language pairs still remains subpar, partly due to the limited ability to handle …
low-resource language pairs still remains subpar, partly due to the limited ability to handle …
Traditional Methods Outperform Generative LLMs at Forecasting Credit Ratings
F Drinkall, JB Pierrehumbert, S Zohren - arXiv preprint arXiv:2407.17624, 2024 - arxiv.org
Large Language Models (LLMs) have been shown to perform well for many downstream
tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre …
tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre …