LEXICAL SELECTION IN MACHINE TRANSLATION OF RUSSIAN-TO-KAZAKH

Öz

This article presents a method of resolving lexical ambiguity of words in an automatic text processing for different groups of natural languages that have not marked corpus. The proposed method is based on creating context vectors by which held the semantic analysis of the text. This method has been successfully applied in the machine translation from Russian into Kazakh. The practical results presented.

Kaynakça

1. Word Sense Disambiguation: Algorithms and Applications (Text, Speech and Language Technology), Ed. by AGIRRE E., EDMONDS P. G..— 1 edition.— Springer, 2007.—November
2. YAROWSKY D., One sense per collocation // HLT ’93: Proceedings of the workshop on Human Language Technology.— Morristown, NJ, USA: Association for Computational Linguistics, 1993.— Pp. 266–271.
3. TURDAKOV D., Recommender System Based on User-generated Content // Proceedings of the SYRCODIS 2007 Colloquium on Databases and Information Systems.— 2007.
4. GALE W. A., CHURCH K. W., YAROWSKY D., A method for disambiguating word senses in a large corpus. // Computers and the Humanitzes.— Vol. 26.— 1993.— Pp. 415–439
5. GALE W. A., CHURCH K. W., YAROWSKY D. One sense per discourse // HLT ’91: Proceedings of the workshop on Speech and Natural Language.— Morristown, NJ, USA: Association for Computational Linguistics, 1992.— Pp. 233–237
6. RICHENS R. H.. Interlingual machine translation // Computer Journal.— Vol. 3.— 1958.— Pp. 144–147.
7. JURAFSKY D., MARTIN J. M., Speech and Language Processing // second edition, Pearson Prentice Hall, New Jersey pp.640644.
8. TUKEYEV U.A. , RAKHIMOVA D.R. et al., Development of morphological analysis and synthesis for machine translation from Russian into Kazakh using multivalued mapping tables. Computer processing of Turkic languages. First International Conference: Proceedings / Astana L.N.Gumilev ENU Publishing House, 2013, 182-191.(in Kazakh)