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.
References
by Method of Near Duplicates Analysis, Proceedings of the 11th IEEE International Conference
on Application of Information and Communication Technologies, AICT2017, Moscow,
Russia, Vol. 2, pp. 363-367. DOI: 10.1109/ICAICT.2017.8686861.
2. Levenshteyn V.I. Dvoichnye kody s ispravleniem vypadeniy, vstavok i zameshcheniy simvolov
[Binary Codes with Correction for Deletions and Insertions of the Symbols], Doklady AN
SSSR [Reports of the USSR Academy of Sciences], 1965, Vol. 163, No. 4, pp. 845-848.
3. Bhattacharyya P. Machine Translation, CRC Press Taylor & Francis Group, 2015, pp. 5-6.
ISBN 9781439897188.
4. Pravila Standartizatsii PR 50.1.027–2014, Pravila okazaniya perevodcheskikh i osobykh vidov
lingvisticheskikh uslug [Standardization Rules PR 50.1.027–2014Rules for the Provision of
Translation and special types of Linguistic Services]. Moscow: Izd-vo FGUP
«Standartinform», 2014, 20 p.
5. Glushan' V.M., Kornilov V.S., Lozovoy A.Yu. Eksperimental'noe opredelenie prigodnosti
pristateynykh annotatsiy k russko-angliyskomu gibridnomu mashinnomu perevodu do i posle
avtomaticheskogo predredaktirovaniya [Experimental Definition of Suitability of the Abstracts
of Papers to the Russian-English Hybrid Machine Translation before and after the Automatic
Pre-editing], Vestnik RGRTU [Bulletin of RSTU], 2019, No. 69, pp. 102-109. DOI:
10.21667/1995-4565-2019-69-102-109.
6. Tsvilling M.Ya., Turover G.Ya. O kriteriyakh otsenki perevoda [About the criteria for assessing
the translation], Tetradi perevodchika [Interpreters' notebooks]. Issue 15. Moscow:
Mezhdunar. Otnosheniya, 1973, pp. 5. Available at: https://wt-blog.net/perevodchiku/okriterijah-
ocenki-perevoda-cvilling-turover.html (accessed 06 November 2019).
7. Maslov S.Yu. Obratnyy metod ustanovleniya vyvodimosti dlya logicheskikh ischisleniy.
Logicheskie i logiko-matematicheskie ischisleniya [An Inverse Method of Establishing Deducibility
for Logical Calculi. Logical and Logical-Mathematical Calculus], Tr. MIAN SSSR [Proceedings
of the Steklov Institute of Mathematics], 1968, No. 98, pp. 26-87.
8. Bobber R.J. Underwater Electroacoustic Measurements, Naval Research Laboratory Underwater
Sound Reference Division Orlando. Florida, 1970, pp. 31-33.
9. Zeng J., Lau T., Lin Sh.-B., Yao Yu. Global Convergence of Block Coordinate Descent in Deep
Learning, Proceedings of the 36th International Conference on Machine Learning. Long
Beach, California. PMLR 97, 2019. Available at: https://arxiv.org/pdf/1803.00225.pdf (accessed
06 November 19).
10. Yu. Nesterov, S. Stich Efficiency of Accelerated Coordinate Descent Method on Structured
Optimization Problems, CORE Discussion Paper, 2016, No. 03. DOI: 10.1137/16M1060182.
11. Potemkin S.B. Mashinnyy perevod kak sredstvo standartizatsii terminologii [Terminology
Database and Machine Translation], Vestnik Moskovskogo gosudarstvennogo oblastnogo
universiteta. Seriya: Lingvistika [Bulletin of the Moscow state regional University. Linguistics
Series], 2017, No. 5, pp. 77-84. DOI: 10.18384/2310-712X-2017-5-77-84.
12. Filippovich Yu.N., Sirenko A.V. Programmnyy kompleks issledovaniy psikholingvisticheskoy
modeli verbal'nogo soznaniya na osnove kognitivnogo i assotsiativnogo eksperimentov [Software
to Research Psycholinguistic Model of Verbal Consciousness based on Cognitive and
Associative Experiments], Voprosy psikholingvistiki [Questions of Psycholinguistics], 2011,
No. 13, pp. 126-139. Available at: https://cyberleninka.ru/article/n/programmnyy-kompleksissledovaniy-
psiholingvisticheskoy-modeli-verbalnogo-soznaniya-na-osnove-kognitivnogo-iassotsiativnogo
(accessed 28 November 19).
13. Vakhrameev M.A. Redaktsionnoe rasstoyanie v svobodnykh levoregulyarnykh svyazkakh [Edit
Distance in Free Left Regular Bands], Vestnik Omskogo universiteta [Bulletin of Omsk University],
2018, Vol. 23, No. 3, pp. 15-19. DOI: 10.25513/1812-3996.2018.23(3).15-19.
14. Ponomareva N.S., Rebrova G.N., Kolina E.A. Primenenie rasstoyaniy redaktirovaniya pri
bioinformatsionnom analize genomov dlya zadach otsenki sostoyaniya reproduktivnoy sistemy
[Application of editing distances in bioinformatic analysis of genomes for problems of evaluating
the state of the reproductive system], Fundamental'nye issledovaniya [Fundamental study],
2015, No. 7-4, pp. 774-777. Available at: https://www.fundamental-research.ru/pdf/2015/7-
4/38819.pdf (accessed 24 November 2019).
15. Chernen'kiy V.M., Gapanyuk Yu.E. Metodika identifikatsii passazhira po ustanovochnym
dannym [Method of Passenger Identification according to Installation Data], Inzhenernyy
zhurnal: nauka i innovatsii [Engineering journal: science and innovation], 2012, Issue 3-89,
pp. 30-39. DOI: 10.18698/2308-6033-2012-3-89.
16. Teorema de Gua [de Goui’sTeorem]. Available at: http://poivs.tsput.ru/Downloads/Article/
5988/Teorema de Gua.pdf (accessed 24 November 2019).
17. Amir-Moéz, A.R.; Byerly, R.E. Pythagorean theorem in unitary spaces, Univ. Beograd. Publ.
Elektrotehn. Fak. Ser. Mat., 1996, No. 7, pp. 85-89. Available at: http://pefmath2.etf.rs/files/
116/844.pdf (accessed 24 November 2019).
18. Kheyfits А. The Theorem of Cosines for Pyramids, The College Mathematics Journal, 2004, Vol.
35, No. 5, pp. 385-388. DOI: 10.2307/4146849.
19. Beck A. The 2-Coordinate Descent Method for Solving Double-Sided Simplex Constrained Minimization
Problems, JOptim. Theory Appl., 2014, Vol. 162, pp. 892-919. DOI10.1007/s10957-013-
0491-5.
20. Nikolaev S.V. Algebraicheskie modeli sistem TSOS: vidy podobiya i kriterii blizosti [Algebraic
Models of DSP Systems: Types of Similarity and Proximity Criteria], Izvestiya TRTU
[Izvestiya TSURE], 2002, No. 1 (24), pp. 108-109.
