scholarly journals A Hybrid Machine Translation System Based on a Monotone Decoder

2019 ◽  
Vol 16 (2) ◽  
pp. 77-90
Author(s):  
hosein khatami ◽  
hakime fadaei ◽  
hesham faili ◽  
◽  
◽  
...  
Keyword(s):  
Machine Translation ◽  
Translation System ◽  
Machine Translation System ◽  
Hybrid Machine ◽  
Hybrid Machine Translation

SisHiTra : A Hybrid Machine Translation System from Spanish to Catalan

2004 ◽  
pp. 349-359 ◽  
Author(s):  
José R. Navarro ◽  
Jorge González ◽  
David Picó ◽  
Francisco Casacuberta ◽  
Joan M. de Val ◽  
...  
Keyword(s):  
Machine Translation ◽  
Translation System ◽  
Machine Translation System ◽  
Hybrid Machine ◽  
Hybrid Machine Translation

An online English-Khmer hybrid machine translation system

2018 ◽  
Vol 17 (3) ◽  
pp. 292
Author(s):  
Javier Sola ◽  
Suos Samak ◽  
Kim Sokphyrum ◽  
Suraiya Jabin ◽  
Niladri Chatterjee
Keyword(s):  
Machine Translation ◽  
Translation System ◽  
Machine Translation System ◽  
Hybrid Machine ◽  
Hybrid Machine Translation

An online English-Khmer hybrid machine translation system

2018 ◽  
Vol 17 (3) ◽  
pp. 292 ◽  
Author(s):  
Suraiya Jabin ◽  
Niladri Chatterjee ◽  
Suos Samak ◽  
Kim Sokphyrum ◽  
Javier Sola
Keyword(s):  
Machine Translation ◽  
Translation System ◽  
Machine Translation System ◽  
Hybrid Machine ◽  
Hybrid Machine Translation

scholarly journals Hybrid Translation with Classification: Revisiting Rule-Based and Neural Machine Translation

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 201
Author(s):  
Jin-Xia Huang ◽  
Kyung-Soon Lee ◽  
Young-Kil Kim
Keyword(s):  
Machine Translation ◽  
Classification Accuracy ◽  
Training Data ◽  
Translation System ◽  
Rule Based ◽  
Neural Machine Translation ◽  
Machine Translation System ◽  
Text Classifiers ◽  
Hybrid Machine Translation ◽  
Translation Accuracy

This paper proposes a hybrid machine-translation system that combines neural machine translation with well-developed rule-based machine translation to utilize the stability of the latter to compensate for the inadequacy of neural machine translation in rare-resource domains. A classifier is introduced to predict which translation from the two systems is more reliable. We explore a set of features that reflect the reliability of translation and its process, and training data is automatically expanded with a small, human-labeled dataset to solve the insufficient-data problem. A series of experiments shows that the hybrid system’s translation accuracy is improved, especially in out-of-domain translations, and classification accuracy is greatly improved when using the proposed features and the automatically constructed training set. A comparison between feature- and text-based classification is also performed, and the results show that the feature-based model achieves better classification accuracy, even when compared to neural network text classifiers.

Sign in / Sign up

Export Citation Format

Share Document