DETERMINING A SET OF CONDITIONS FOR AUTOMATICALLY FINDING THE BEST OPTION FOR HYBRID MACHINE TRANSLATION OF TEXT AT THE LEVELOF GRAPHEMES

Abstract

The article is devoted to the Algorithmic Search for Optimal Solutions for evaluating and
improving the Quality of Hybrid Machine Translation of Text. The Object of the Research is Texts
on any Alphabetical Languages with different Bases (Alphabets), as well as their Translations into
other Alphabetical Languages.Currently, existing Methods and Means of Hybrid Machine Translation
are characterized by a wide variety of Quality Assessment Algorithms, but the Disadvantage
of these Methods is that most of them do not have Clear Criteria, Limitations and Schemes of Assessments,
eventually, the Result of the Translation in most cases does not correspond to the Level
of Publication. The Aim of the Work is to determine a Set of Conditions for automatic search for
the Best Option of Hybrid Machine Translation of Text at the Level of Graphemes.The Main Tasks
to be solved during the Research are the Search for Qualitative and Quantitative Conditions, including
the maximum, minimum and average values of the Lengths of Translations, Reverse Translations
and Editorial Distances between Pairs of Texts that have the Same Meaning. The Scientific
Novelty lies in use the Graphical Representation of the Model of Alphabetic Languages at the
Level of Graphemes in the Form of a Cartesian Coordinate System with a Dimension equal to a
Unit Editorial Distance (by Levenstein). When solving the de Goui’s Theorem, the current Rules ofStandardization PR 50.1.027–2014 "Rules for the Provision of Translation and Special Types of
Linguistic Services", the Method of Decanonicalization and the Model "Original Text – Translation
– Reverse Translation" were used. As a Result, Actual and Practically Applicable Solutions
for the Problems under consideration are obtained. In this regard; this Work may be interest to a
wide range of Specialists engaged in Machine Translation and Translation Studies.