ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Hybrid Translation with Classification: Revisiting Rule-Based and Neural Machine Translation
Cited 16 time in scopus Download 180 time Share share facebook twitter linkedin kakaostory
Authors
Jin-Xia Huang, Kyung-Soon Lee, Young-Kil Kim
Issue Date
2020-02
Citation
Electronics, v.9, no.2, pp.1-16
ISSN
2079-9292
Publisher
MDPI
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.3390/electronics9020201
Abstract
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.
KSP Keywords
Hybrid system, Machine Translation(MT), Neural Machine Translation, Rule-based, Text classifiers, Translation Accuracy, Translation system, classification accuracy, feature-based model, hybrid machine, hybrid translation
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
CC BY