Authors:
- Nominated by Tsinghua University as an outstanding Ph.D. thesis
- Reports on current challenges and important advances in neural machine translation
- Addresses training jointly bidirectional neural machine translation models
- Incorporates additional monolingual and bilingual corpora into neural machine translation
Part of the book series: Springer Theses (Springer Theses)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (7 chapters)
-
Front Matter
About this book
This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.
Authors and Affiliations
-
Google, Beijing, China
Yong Cheng
About the author
Yong Cheng is currently a software engineer engaged in research at Google. Before joining Google, he worked as a senior researcher at Tencent AI Lab. He obtained his Ph.D. from the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University in 2017. His research interests focus on neural machine translation and natural language processing.
Bibliographic Information
Book Title: Joint Training for Neural Machine Translation
Authors: Yong Cheng
Series Title: Springer Theses
DOI: https://doi.org/10.1007/978-981-32-9748-7
Publisher: Springer Singapore
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer Nature Singapore Pte Ltd. 2019
Hardcover ISBN: 978-981-32-9747-0Published: 06 September 2019
eBook ISBN: 978-981-32-9748-7Published: 26 August 2019
Series ISSN: 2190-5053
Series E-ISSN: 2190-5061
Edition Number: 1
Number of Pages: XIII, 78
Number of Illustrations: 14 b/w illustrations, 9 illustrations in colour