Automatic evaluating of Russian-Arabic machine translation quality using METEOR method
Diadeen Ali Hameed, Tahseen Ameen Faisal, Ali Mustafa Ali Alshaykha, Ghanim Thiab Hasan, Harith Abdullah Ali · AIP conference proceedings · 2022
Given the huge development in the field of machine translation (MT) system and the emergence of the need for high speed and extreme accuracy in the transmission of information from one language to another, the need to design an optimum new systems and compare them with the traditional available systems to determine the efficiency of the new systems and identify the weaknesses to be developed in the proposed new systems. The aim of this work is to conduct an evaluation study of the performance and efficiency of the RAMT system. The evaluation has been conducted by comparing this system with the well-known google translation system by conducting a translation of 1000 Russian sentences in METEOR (Metric for Evaluation of Translation with Explicit ORdering) method. The obtain results show that the RAMT system efficiency is about 51.57%, while the efficiency of Google translation’s system is about 48.43%. The comparison results indicate that the RAMT system is more effective and give a better translation accuracy than the Google translations system.