Neural Machine Translation Techniques for Named Entity Transliteration

NAMED ENTITIES, pp. 89-94, 2018.

Cited by: 1|Views31
EI

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...More

Code:

Data:

Your rating :
0

 

Tags
Comments