Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Thanh Le, Ha"'
Publikováno v:
IEEE Access, Vol 11, Pp 11675-11684 (2023)
Old photos that were captured about a century ago have archaeological and historical significance. Many of the old photos have been successfully digitized, but most of them suffer from severe and complicated distortion. Thus, prior studies have focus
Externí odkaz:
https://doaj.org/article/e0fd749384be45ecb6b490dc3da2b92a
Autor:
Thanh Le, Ha
Publikováno v:
Entrepreneurial Business and Economics Review. 10(1):7-22
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=1063261
Autor:
Ferrer, Alice Joan G., Thanh, Le Ha, Kiet, Nguyen Tuan, Chuong, Pham Hong, Trang, Vu Thu, Hopanda, Jinky C., Carmelita, Benedict Mark, Gummadi, Sridhar, Bernardo, Eisen Bernard
Publikováno v:
In Economic Analysis and Policy March 2022 73:639-652
Publikováno v:
Applied Artificial Intelligence, Vol 36, Iss 1 (2022)
Data sparsity is one of the challenges for low-resource language pairs in Neural Machine Translation (NMT). Previous works have presented different approaches for data augmentation, but they mostly require additional resources and obtain low-quality
Externí odkaz:
https://doaj.org/article/e2759d6be0ef4ca4959cff14e6be5972
Autor:
Ferrer, Alice Joan G., Thanh, Le Ha, Chuong, Pham Hong, Kiet, Nguyen Tuan, Trang, Vu Thu, Duc, Trinh Cong, Hopanda, Jinky C., Carmelita, Benedict Mark, Bernardo, Eisen Bernard
Publikováno v:
Asia-Pacific Journal of Regional Science; Jun2023, Vol. 7 Issue 2, p641-663, 23p
Publikováno v:
IWSLT
This paper contains the description for the submission of Karlsruhe Institute of Technology (KIT) for the multilingual TEDx translation task in the IWSLT 2021 evaluation campaign. Our main approach is to develop both cascade and end-to-end systems an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6801842643f19060c203ef15c5d0f24e
https://doi.org/10.18653/v1/2021.iwslt-1.18
https://doi.org/10.18653/v1/2021.iwslt-1.18
Autor:
Ngoc-Quan Pham, Tuan Nam Nguyen, Christian Huber, Sebastian Stüker, Thanh-Le Ha, Thai-Son Nguyen, Felix Schneider
Publikováno v:
IWSLT
This paper describes KIT’submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d2dae6a8305313aca7ce6f00b836e0f
https://doi.org/10.18653/v1/2021.iwslt-1.13
https://doi.org/10.18653/v1/2021.iwslt-1.13
Autor:
Tuan-Nam Nguyen, Ngoc-Quan Pham, Alex Waibel, Thai-Son Nguyen, Thanh-Le Ha, Sebastian Stüker, Jan Niehues, Elizabeth Salesky
Publikováno v:
INTERSPEECH
INTERSPEECH 2020 Proceedings, 31-35
STARTPAGE=31;ENDPAGE=35;TITLE=INTERSPEECH 2020 Proceedings
INTERSPEECH 2020 Proceedings, 31-35
STARTPAGE=31;ENDPAGE=35;TITLE=INTERSPEECH 2020 Proceedings
Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text modeling, and t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3732060e00671f53837d78662fdb38f5
https://doi.org/10.21437/interspeech.2020-2526
https://doi.org/10.21437/interspeech.2020-2526
Autor:
Sebastian Stüker, Tuan-Nam Nguyen, Alex Waibel, Maximilian Awiszus, Ngoc-Quan Pham, Thai-Son Nguyen, Felix Schneider, Thanh-Le Ha
Publikováno v:
IWSLT
This paper describes KIT’s submissions to the IWSLT2020 Speech Translation evaluation campaign. We first participate in the simultaneous translation task, in which our simultaneous models are Transformer based and can be efficiently trained to obta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca95bf41c9ee7a204dc781f9ef6c21a5
https://doi.org/10.18653/v1/2020.iwslt-1.4
https://doi.org/10.18653/v1/2020.iwslt-1.4
Publikováno v:
WAT@EMNLP-IJCNLP
Among the six challenges of neural machine translation (NMT) coined by (Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2eb75765412874ad9d793f816bc6da4b
http://arxiv.org/abs/1910.03467
http://arxiv.org/abs/1910.03467
