­
­
­
­

Inventi Impact: Machine Vision

Articles

  • Inventi:emv/28389/19
    A Neural Machine Translation Model for Arabic Dialects That Utilizes Multitask Learning (MTL)
    Research 2019 : April - June
    Laith H Baniata, Seyoung Park, Seong-Bae Park

    In this research article, we study the problem of employing a neural machine translation model to translate Arabic dialects to\nModern Standard Arabic. The proposed solution of the neural machine translation model is prompted by the recurrent neural\nnetwork-based encoder-decoder neural machine translation model that has been proposed recently, which generalizes machine\ntranslation as sequence learning problems. We propose the development of a multitask learning (MTL) model which shares one\ndecoder among language pairs, and every source language has a separate encoder.The proposed model can be applied to limited\nvolumes of data aswell as extensive amounts of data. Experiments carried out have shown that the proposed MTL model can ensure\na higher quality of translation when compared to the individually learned model.

    How to Cite this Article
    CC Compliant Citation: Laith H. Baniata, Seyoung Park, and Seong-\nBae Park, â??A Neural Machine Translation Model for Arabic\nDialects That Utilizes Multitask Learning (MTL),â? Computational\nIntelligence and Neuroscience, vol. 2018, Article ID 7534712, 10\npages, 2018. https://doi.org/10.1155/2018/7534712, http://\ncreativecommons.org/licenses/by/4.0/.
    Download Full Text