Arabic–Chinese Neural Machine Translation: Romanized Arabic as Subword Unit for Arabic-sourced Translation

Arabic–Chinese Neural Machine Translation: Romanized Arabic as Subword Unit for Arabic-sourced Translation

Morphologically rich and complex languages such as Arabic, pose a major challenge to neural machine translation (NMT) due to the large number of rare words and the inability of NMT to translate them. Unknown word (UNK) symbols are used to represent out-of-vocabulary words because NMT typically opera...

Full description

Bibliographic Details
Main Authors: Fares Aqlan, Xiaoping Fan, Abdullah Alqwbani, Akram Al-Mansoub
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Arabic morphology
Arabic romanization
BPE
data filtering
linguistic feature
morphological segmentation
Online Access:https://ieeexplore.ieee.org/document/8835016/

Internet

https://ieeexplore.ieee.org/document/8835016/

Similar Items