Automatic Transliteration of Polish and English Proper Nouns into Lithuanian

Authors

  • Pijus Kasparaitis

DOI:

https://doi.org/10.5755/j01.itc.52.1.32353

Keywords:

Natural Language Processing, machine translation, machine transliteration, context-sensitive rules, context-free rules, Lithuanian

Abstract

As the world is becoming more globalized, proper nouns move from one language into other languages. In order to preserve the grammatical or phonetic structure of the target language, a desire arises to adapt them. The present work deals with adaptation (transliteration) of Polish and English words to the Lithuanian language. The set of context-sensitive and context-free rules was created manually for the Polish language. Manually creating such rules for the English language is too difficult, thus the algorithm to automatically generate transliteration rules from English-Lithuanian word pairs aligned at the letter level was developed in this work. For the Polish language, 100% accuracy was achieved. For English, word accuracy of about 50% and character accuracy of about 90% was achieved. The reasons for this accuracy are identified and directions for improving the set of rules are provided.

Downloads

Published

2023-03-28

Issue

Section

Articles