A Novel Deep Learning Method for Obtaining Bilingual Corpus from Multilingual Website
Joint Authors
Li, Xiao
Yang, Yating
Wang, Lei
Zhu, ShaoLin
Mi, ChengGang
Source
Mathematical Problems in Engineering
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-7, 7 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-01-10
Country of Publication
Egypt
No. of Pages
7
Main Subjects
Abstract EN
Machine translation needs a large number of parallel sentence pairs to make sure of having a good translation performance.
However, the lack of parallel corpus heavily limits machine translation for low-resources language pairs.
We propose a novel method that combines the continuous word embeddings with deep learning to obtain parallel sentences.
Since parallel sentences are very invaluable for low-resources language pair, we introduce cross-lingual semantic representation to induce bilingual signals.
Our experiments show that we can achieve promising results under lacking external resources for low-resource languages.
Finally, we construct a state-of-the-art machine translation system in low-resources language pair.
American Psychological Association (APA)
Zhu, ShaoLin& Li, Xiao& Yang, Yating& Wang, Lei& Mi, ChengGang. 2019. A Novel Deep Learning Method for Obtaining Bilingual Corpus from Multilingual Website. Mathematical Problems in Engineering،Vol. 2019, no. 2019, pp.1-7.
https://search.emarefa.net/detail/BIM-1197031
Modern Language Association (MLA)
Zhu, ShaoLin…[et al.]. A Novel Deep Learning Method for Obtaining Bilingual Corpus from Multilingual Website. Mathematical Problems in Engineering No. 2019 (2019), pp.1-7.
https://search.emarefa.net/detail/BIM-1197031
American Medical Association (AMA)
Zhu, ShaoLin& Li, Xiao& Yang, Yating& Wang, Lei& Mi, ChengGang. A Novel Deep Learning Method for Obtaining Bilingual Corpus from Multilingual Website. Mathematical Problems in Engineering. 2019. Vol. 2019, no. 2019, pp.1-7.
https://search.emarefa.net/detail/BIM-1197031
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1197031