Výsledky vyhledávání

Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition

Autor: Hwichan Kim, Mamoru Komachi, Tosho Hirasawa

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

Zobrazit plný text záznamu

TMU NMT System with Japanese BART for the Patent task of WAT 2021

Autor: Mamoru Komachi, Hwichan Kim

Publikováno v: Scopus-Elsevier
WAT@ACL/IJCNLP

In this paper, we introduce our TMU Neural Machine Translation (NMT) system submitted for the Patent task (Korean Japanese and English Japanese) of 8th Workshop on Asian Translation (Nakazawa et al., 2021). Recently, several studies proposed pre-trai

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a13f5ddf65ae222782d4d7adbb3e625
http://www.scopus.com/inward/record.url?eid=2-s2.0-85138332995&partnerID=MN8TOARS

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání