Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lukas Edman"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 12 (2024)
Externí odkaz:
https://doaj.org/article/6a83d12d8d8a48e48bc6d9df2f23df8a
Publikováno v:
University of Groningen
WMT (2)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2, 386-392
WMT (2)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2, 386-392
This paper presents the systems submitted by the University of Groningen to the English-Kazakh language pair (both translation directions) for the WMT 2019 news translation task. We explore the potential benefits of (i) morphological segmentation (bo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab67320857cd4c4e6dab25418de964fd
https://research.rug.nl/en/publications/66a779dd-8773-4d94-837f-5e3e3d5dbce1
https://research.rug.nl/en/publications/66a779dd-8773-4d94-837f-5e3e3d5dbce1
Publikováno v:
University of Groningen
This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available. We find that, in very low resource scenarios, statistical n-gram language models outperform state-of-the-art neural models. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fab091f381bee7ee94794d7f8ef1cd98
https://research.rug.nl/en/publications/f6ed7384-8c3c-4914-a771-ae3a5ad6dfd5
https://research.rug.nl/en/publications/f6ed7384-8c3c-4914-a771-ae3a5ad6dfd5
Publikováno v:
Proceedings of the Fifth Conference on Machine Translation (WMT), 1099-1103
STARTPAGE=1099;ENDPAGE=1103;TITLE=Proceedings of the Fifth Conference on Machine Translation (WMT)
University of Groningen
STARTPAGE=1099;ENDPAGE=1103;TITLE=Proceedings of the Fifth Conference on Machine Translation (WMT)
University of Groningen
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2020 Unsupervised Machine Translation task for German--Upper Sorbian. We investigate the usefulness of data selection in the unsupervised setting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4e4ad0d1cf2883168e60b1c2a8b38acb
https://research.rug.nl/en/publications/a8807965-a6d5-4ac5-90f7-321995955ebc
https://research.rug.nl/en/publications/a8807965-a6d5-4ac5-90f7-321995955ebc
Publikováno v:
University of Groningen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::57648807818f8650694dbc1bed1f975f
https://research.rug.nl/en/publications/680bb044-42d6-4f27-9a25-236912b32c17
https://research.rug.nl/en/publications/680bb044-42d6-4f27-9a25-236912b32c17
Publikováno v:
University of Groningen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4fc67414bc52c8ea0599a4e5c14370a8
https://research.rug.nl/en/publications/306c8b16-d690-45e1-bd92-10acbfb3273b
https://research.rug.nl/en/publications/306c8b16-d690-45e1-bd92-10acbfb3273b
Publikováno v:
University of Groningen
Proceedings of the Fifth Conference on Machine Translation (WMT), 274-281
STARTPAGE=274;ENDPAGE=281;TITLE=Proceedings of the Fifth Conference on Machine Translation (WMT)
Proceedings of the Fifth Conference on Machine Translation (WMT), 274-281
STARTPAGE=274;ENDPAGE=281;TITLE=Proceedings of the Fifth Conference on Machine Translation (WMT)
Translating to and from low-resource polysynthetic languages present numerous challenges for NMT. We present the results of our systems for the English--Inuktitut language pair for the WMT 2020 translation tasks. We investigated the importance of cor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9ecd58399fcf0289fbc5c12b0518484e
https://research.rug.nl/en/publications/ce246963-3b30-4064-ab65-ae9e5e506c5e
https://research.rug.nl/en/publications/ce246963-3b30-4064-ab65-ae9e5e506c5e