Alignment of Word Combinations in Uzbek and English
Keywords:
alignment, word combination, tokenization, source language, target language (TL), grammatical structure, semanticsAbstract
In various fields of natural language processing (NLP), especially in machine translation, achieving accurate alignment of parallel texts requires a deep understanding of the expressions, grammatical structures, and semantics in both the source and target languages. Although Uzbek and English share a structural similarity in their use of head and subordinate words within phrases, English uniquely features compound word combinations as well. In Uzbek, word combinations are classified based on the grammatical properties and structures of their components. Specifically, the classification relies on the part of speech of the dominant element and the syntactic role of the subordinate element. During alignment, differences arise due to the grammatical characteristics of the words making up the phrases in each language and their syntactic positions within sentences.
References
MacCartney B., Galley M., Manning Ch. “A Phrase-Based Alignment Model for Natural Language Inference”. Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing. 2008.
Matyakubova N., Xamroyeva Sh., Dauletov A., Mengliyev B., Adali E. “Algorithm of Creating The “Uzbek-English Aligner” Program”. 6.IEEE - UBMK-2023 VIII. Uluslararası Bilgisayar Bilimleri ve Mühendisliği Konferansı - XII. Pp 114-118. 2023.
Abdullayev F.A. “Grammar of the Uzbek language”. Vol. 2, Syntax. pp18-39. 1976.
Brinton L. J. “The Structure of Modern English” John Benjamins Publishing Company Amsterdam /Philadelphia.2000.
Arase Y., Tsujii J., “Compositional Phrase Alignment and Beyond”. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, November 16–20, 2020.
Abdullayeva O., Xudayarova S. “The problem of definition, description and classification of the phrase in Uzbek linguistics”. International scientific-theoretical conference on the topic: «Problems of research and education of the Uzbek language».
Aarts B., Haegeman L., “English Word Classes and Phrases”, Bas Aarts and Liliane Haegeman. January 2008.
Nwet K. Th. “Developing Word to Phrase Alignment for Myanmar-English Machine Translation”, 13th International Conference on Computer Applications 2015.
Sennrich R., Martin V. “Iterative, MT-based sentence alignment of parallel texts.” In: NODALIDA 2011, Nordic Conference of Computational Linguistics, Riga, 11 May 2011.
