Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data

Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data

Despite the many proposals to solve the neural machine translation (NMT) problem of low-resource languages, it continues to be difficult. The issue becomes even more complicated when few resources cover only a single domain. In this paper, we discuss the applicability of a source-side monolingual da...

Full description

Bibliographic Details
Main Authors: Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh, Grigori Sidorov
Format: Article
Language:English
Published: MDPI AG 2023-01-01
Series:Applied Sciences
Subjects:
Wolaytta–English NMT
English–Wolaytta NMT
low-resource NMT
self-learning
neural machine translation
monolingual data for low-resource languages
Online Access:https://www.mdpi.com/2076-3417/13/2/1201

Internet

https://www.mdpi.com/2076-3417/13/2/1201

Similar Items