Findings of the first shared task on machine translation robustness
We share the findings of the first shared task on improving robustness of Machine
Translation (MT). The task provides a testbed representing challenges facing MT models …
Translation (MT). The task provides a testbed representing challenges facing MT models …
Improving neural machine translation robustness via data augmentation: Beyond back translation
Neural Machine Translation (NMT) models have been proved strong when translating clean
texts, but they are very sensitive to noise in the input. Improving NMT models robustness can …
texts, but they are very sensitive to noise in the input. Improving NMT models robustness can …
Utnlp at semeval-2022 task 6: A comparative analysis of sarcasm detection using generative-based and mutation-based data augmentation
Sarcasm is a term that refers to the use of words to mock, irritate, or amuse someone. It is
commonly used on social media. The metaphorical and creative nature of sarcasm presents …
commonly used on social media. The metaphorical and creative nature of sarcasm presents …
A survey of domain adaptation for machine translation
Neural machine translation (NMT) is a deep learning based approach for machine
translation, which outperforms traditional statistical machine translation (SMT) and yields the …
translation, which outperforms traditional statistical machine translation (SMT) and yields the …
The source-target domain mismatch problem in machine translation
While we live in an increasingly interconnected world, different places still exhibit strikingly
different cultures and many events we experience in our every day life pertain only to the …
different cultures and many events we experience in our every day life pertain only to the …
Multimodal robustness for neural machine translation
Y Zhao, I Calapodescu - Proceedings of the 2022 conference on …, 2022 - aclanthology.org
In this paper, we look at the case of a Generic text-to-text NMT model that has to deal with
data coming from various modalities, like speech, images, or noisy text extracted from the …
data coming from various modalities, like speech, images, or noisy text extracted from the …
Fine-tuning MT systems for robustness to second-language speaker variations
MMI Alam, A Anastasopoulos - … of the Sixth Workshop on Noisy …, 2020 - aclanthology.org
The performance of neural machine translation (NMT) systems only trained on a single
language variant degrades when confronted with even slightly different language variations …
language variant degrades when confronted with even slightly different language variations …
Learning from Wrong Predictions in Low-Resource Neural Machine Translation
JC Hu, R Cavicchioli, G Berardinelli… - Proceedings of the …, 2024 - aclanthology.org
Abstract Resource scarcity in Neural Machine Translation is a challenging problem in both
industry applications and in the support of less-spoken languages represented, in the worst …
industry applications and in the support of less-spoken languages represented, in the worst …
Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make
models robust, we generate adversarial augmentation samples that attack the model and …
models robust, we generate adversarial augmentation samples that attack the model and …
[PDF][PDF] Low-resource Neural Machine Translation from Finnish to Chinese
Z Gu - helda.helsinki.fi
Machine translation (MT), a branch of artificial intelligence and computational linguistics,
uses algorithms and models to automatically translate text from one language to another …
uses algorithms and models to automatically translate text from one language to another …