Neural Machine Translation Techniques for Named Entity Transliteration
TL
TL;DR
This work applies well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation to build a strong transliteration system.
Abstract
Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models. To build a strong transliteration system, we apply well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation. Our submission to the NEWS 2018 Shared Task on Named Entity Transliteration ranked first in several tracks.
References36 items
1
Marian: Fast Neural Machine Translation in C++
2
The University of Edinburgh’s Neural MT Systems for WMT17
3
Deep architectures for Neural Machine Translation
4
Stronger Baselines for Trustable Results in Neural Machine Translation
5