Neural Network Machine Translation Method Based on Unsupervised Domain Adaptation
Author
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-12-24
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
Relying on large-scale parallel corpora, neural machine translation has achieved great success in certain language pairs.
However, the acquisition of high-quality parallel corpus is one of the main difficulties in machine translation research.
In order to solve this problem, this paper proposes unsupervised domain adaptive neural network machine translation.
This method can be trained using only two unrelated monolingual corpora and obtain a good translation result.
This article first measures the matching degree of translation rules by adding relevant subject information to the translation rules and dynamically calculating the similarity between each translation rule and the document to be translated during the decoding process.
Secondly, through the joint training of multiple training tasks, the source language can learn useful semantic and structural information from the monolingual corpus of a third language that is not parallel to the current two languages during the process of translation into the target language.
Experimental results show that better results can be obtained than traditional statistical machine translation.
American Psychological Association (APA)
Wang, Rui. 2020. Neural Network Machine Translation Method Based on Unsupervised Domain Adaptation. Complexity،Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1143144
Modern Language Association (MLA)
Wang, Rui. Neural Network Machine Translation Method Based on Unsupervised Domain Adaptation. Complexity No. 2020 (2020), pp.1-11.
https://search.emarefa.net/detail/BIM-1143144
American Medical Association (AMA)
Wang, Rui. Neural Network Machine Translation Method Based on Unsupervised Domain Adaptation. Complexity. 2020. Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1143144
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1143144