Pre-training neural machine translation with alignment information via optimal transport
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AU7CVNATW" target="_blank" >RIV/00216208:11320/23:U7CVNATW - isvavai.cz</a>
Result on the web
<a href="https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1" target="_blank" >https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s11042-023-17479-z" target="_blank" >10.1007/s11042-023-17479-z</a>
Alternative languages
Result language
angličtina
Original language name
Pre-training neural machine translation with alignment information via optimal transport
Original language description
"With the rapid development of globalization, the demand for translation between different languages is also increasing. Although pre-training has achieved excellent results in neural machine translation, the existing neural machine translation has almost no high-quality suitable for specific fields. Alignment information, so this paper proposes a pre-training neural machine translation with alignment information via optimal transport. First, this paper narrows the representation gap between different languages by using OTAP to generate domain-specific data for information alignment, and learns richer semantic information. Secondly, this paper proposes a lightweight model DR-Reformer, which uses Reformer as the backbone network, adds Dropout layers and Reduction layers, reduces model parameters without losing accuracy, and improves computational efficiency. Experiments on the Chinese and English datasets of AI Challenger 2018 and WMT-17 show that the proposed algorithm has better performance than existing algorithms."
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
"MULTIMEDIA TOOLS AND APPLICATIONS"
ISSN
1380-7501
e-ISSN
—
Volume of the periodical
""
Issue of the periodical within the volume
2023-11-2
Country of publishing house
US - UNITED STATES
Number of pages
21
Pages from-to
1-21
UT code for WoS article
001096936900014
EID of the result in the Scopus database
—