Domain Adaptive Inference for Neural Machine Translation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427126" target="_blank" >RIV/00216208:11320/19:10427126 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/P19-1022" target="_blank" >https://www.aclweb.org/anthology/P19-1022</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Domain Adaptive Inference for Neural Machine Translation
Original language description
We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing performance on the original domain. We adapt sequentially across two Spanish-English and three English-German tasks, comparing unregularized fine-tuning, L2 and Elastic Weight Consolidation. We then report a novel scheme for adaptive NMT ensemble decoding by extending Bayesian Interpolation with source information, and report strong improvements across test domains without access to the domain label.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
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
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů