REAL

Transcribe.mari-language.com : Automatic transcriptions and transliterations for ten languages of Russia

Bradley, Jeremy (2017) Transcribe.mari-language.com : Automatic transcriptions and transliterations for ten languages of Russia. Acta Linguistica Academica, 64 (3). pp. 369-382. ISSN 2559-8201

[img]
Preview
Text
2062.2017.64.3.3.pdf

Download (145kB) | Preview

Abstract

The aim of this paper is to introduce my efforts to create server-sided (i.e., platform independent web-based, from a user’s perspective) automatic transcription and transliteration software for Uralic and non-Uralic languages of Russia. For ten literary standards — Meadow Mari, Hill Mari, Komi, Udmurt, Erzya, Moksha, Russian, Tatar, Bashkir, Chuvash — an operational interface can be found at transcribe.mari-language.com and the source code at source.mari-language.com, published under a Creative Commons license. This paper details many of the fine aspects of writing systems used for (Meadow) Mari that I had to take into consideration when creating transcription mechanisms for that language.

Item Type: Article
Subjects: P Language and Literature / nyelvészet és irodalom > P0 Philology. Linguistics / filológia, nyelvészet
Depositing User: László Sallai-Tóth
Date Deposited: 06 Oct 2017 06:47
Last Modified: 30 Sep 2019 23:15
URI: http://real.mtak.hu/id/eprint/65043

Actions (login required)

Edit Item Edit Item