Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Tosho Hirasawa"'
Publikováno v:
IEEE Access, Vol 10, Pp 67653-67668 (2022)
Multimodal machine translation (MMT) is an attractive application of neural machine translation (NMT) that is commonly incorporated with image information. However, the MMT models proposed thus far have only comparable or slightly better performance
Externí odkaz:
https://doaj.org/article/c996a3532f6d4e9eac466d2220e98638
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Journal of Information Processing. 30:388-396
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a0f6ddd7759de821dc0db5a2ae2ea72
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100876110
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100876110
Publikováno v:
WAT@ACL/IJCNLP
Scopus-Elsevier
Scopus-Elsevier
We introduce our TMU Japanese-to-English system, which employs a semi-autoregressive model, to tackle the WAT 2021 restricted translation task. In this task, we translate an input sentence with the constraint that some words, called restricted target
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1de5617c9d13badff81d05c010ef3bba
https://doi.org/10.18653/v1/2021.wat-1.5
https://doi.org/10.18653/v1/2021.wat-1.5
Publikováno v:
ACL (student)
The primary limitation of North Korean to English translation is the lack of a parallel corpus; therefore, high translation accuracy cannot be achieved. To address this problem, we propose a zero-shot approach using South Korean data, which are remar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::202305db238c3132ad9023d21fe302a3
https://doi.org/10.18653/v1/2020.acl-srw.11
https://doi.org/10.18653/v1/2020.acl-srw.11
Publikováno v:
NGT@ACL
We introduce our TMU system that is submitted to The 4th Workshop on Neural Generation and Translation (WNGT2020) to English-to-Japanese (En→Ja) track on Simultaneous Translation And Paraphrase for Language Education (STAPLE) shared task. In most c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abef7442c1ff22519c7a636473133eb1
https://doi.org/10.18653/v1/2020.ngt-1.15
https://doi.org/10.18653/v1/2020.ngt-1.15
Publikováno v:
NAACL-HLT (Student Research Workshop)
Scopus-Elsevier
Scopus-Elsevier
Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from a shortage
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d45a3cfe6ad32afe1c4ffe8cb6027f86
https://doi.org/10.18653/v1/n19-3012
https://doi.org/10.18653/v1/n19-3012
Publikováno v:
Scopus-Elsevier
NAACL-HLT (Student Research Workshop)
NAACL-HLT (Student Research Workshop)
Recently, neural machine translation is widely used for its high translation accuracy, but it is also known to show poor performance at long sentence translation. Besides, this tendency appears prominently for low resource languages. We assume that t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::407213fd33c48311139a7ff597cd0d17
http://www.scopus.com/inward/record.url?eid=2-s2.0-85115883423&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85115883423&partnerID=MN8TOARS
