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 …
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 …
Analyzing Challenges in Neural Machine Translation for Software Localization
Abstract Advancements in Neural Machine Translation (NMT) greatly benefit the software
localization industry by decreasing the post-editing time of human annotators. Although the …
localization industry by decreasing the post-editing time of human annotators. Although the …
Biomedical Parallel Sentence Retrieval using Large Language Models
We have explored the effect of in domain knowledge during parallel sentence filtering from
in domain corpora. Models built with sentences mined from in domain corpora without …
in domain corpora. Models built with sentences mined from in domain corpora without …
Learning from Mistakes: Towards Robust Neural Machine Translation for Disfluent L2 Sentences
We study the sentences written by second-language (L2) learners to improve the robustness
of current neural machine translation (NMT) models on this type of data. Current large …
of current neural machine translation (NMT) models on this type of data. Current large …
FJWU participation for the WMT20 Biomedical Translation Task
S Naz, S Abdul-Rauf, SU Haq - Proceedings of the Fifth …, 2020 - aclanthology.org
This paper reports system descriptions for FJWU-NRPU team for participation in the WMT20
Biomedical shared translation task. We focused our submission on exploring the effects of …
Biomedical shared translation task. We focused our submission on exploring the effects of …
[PDF][PDF] Curriculum VitæEtendu
F Yvon - 2022 - fyvo.github.io
2013- Directeur de recherche au CNRS, chercheur au LIMSI (LISN depuis janvier 2021)
dans le groupe “Traitement du Langage Parlé”. Entre juin 2013 et décembre 2019, j'ai été …
dans le groupe “Traitement du Langage Parlé”. Entre juin 2013 et décembre 2019, j'ai été …
[PDF][PDF] Domain Adaptation for Automated Program Repair
A Zirak - 2022 - prism.ucalgary.ca
Abstract Automated Program Repair (APR) is defined as the process of fixing a bug/defect in
the source code, by an automated tool. APR methods have recently experienced promising …
the source code, by an automated tool. APR methods have recently experienced promising …
LIMSI@ MLIA
This report describes LIMSI's submissions to the Round 1 of translation shared task at MLIA.
We have submitted systems using various combinations of in-domain and out-of-domain …
We have submitted systems using various combinations of in-domain and out-of-domain …