TY - GEN
T1 - Numerical methods for retrieval and adaptation in Nagao’s EBMT model
AU - He, Kun
AU - Zhao, Tianjing
AU - Lepage, Yves
N1 - Funding Information:
This research was supported in part by the Japanese Society for the Promotion of Science (JSPS) under grant 18K11447 entitled: Self-explainable and fast-to-train example-based machine translation using neural networks.
Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/17
Y1 - 2019/1/17
N2 - We build an example-based machine translation system. It is an instance of case-based reasoning for machine translation. We introduce numerical methods instead of symbolic methods in two steps: retrieval and adaptation. For retrieval, we test three different approaches to define similarity between sentences. For adaptation, we use neural networks to solve analogies between sentences across languages. Oracle experiments allow to identify the best retrieval technique and to estimate the possibilities of such an approach. The system could place itself between a statistical and a neural machine translation systems on a task with not so large data.
AB - We build an example-based machine translation system. It is an instance of case-based reasoning for machine translation. We introduce numerical methods instead of symbolic methods in two steps: retrieval and adaptation. For retrieval, we test three different approaches to define similarity between sentences. For adaptation, we use neural networks to solve analogies between sentences across languages. Oracle experiments allow to identify the best retrieval technique and to estimate the possibilities of such an approach. The system could place itself between a statistical and a neural machine translation systems on a task with not so large data.
KW - Example-based machine translation
KW - Numerical methods
UR - http://www.scopus.com/inward/record.url?scp=85062396944&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062396944&partnerID=8YFLogxK
U2 - 10.1109/ICACSIS.2018.8618226
DO - 10.1109/ICACSIS.2018.8618226
M3 - Conference contribution
AN - SCOPUS:85062396944
T3 - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
SP - 195
EP - 200
BT - 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
Y2 - 27 October 2018 through 28 October 2018
ER -