Show Less
Restricted access

Translation Studies and Translation Practice: Proceedings of the 2nd International TRANSLATA Conference, 2014

Part 1

Series:

Edited By Lew N. Zybatow, Andy Stauder and Michael Ustaszewski

TRANSLATA II was the second in a series of triennial conferences on Translation and Interpreting Studies, held at the University of Innsbruck. The series is conceptualized as a forum for Translation Studies research. The contributions to this volume focus on humo(u)r translation, legal translation, and human-machine interaction in translation. The contributors also regard computer-aided translation, specialised translation, terminology as well as audiovisual translation and professional aspects in translation and interpreting.

Show Summary Details
Restricted access

DIRETRA, a Customizable Direct Translation System: First Sketches (Alëna Aksënova / Marina Ermolaeva)

Extract

Alëna Aksënova & Marina Ermolaeva, Lomonosov Moscow State University

DIRETRA, a Customizable Direct Translation System: First Sketches

Abstract: DIRETRA is a direct translation system designed for Turkic languages. The goal is to provide a word-for-word translation of a given text, reflecting all the morphological phenomena of the source language. The structure of the system is shown using the example of Turkish nominal inflection.

1. Introduction

DIRETRA is a direct translation system designed for Turkic languages. Turkic languages are agglutinative and have rich and complex morphology; therefore, the primary goal is to provide a word-for-word translation of a given text, reflecting the morphological phenomena of the source language (SL) as precisely as possible.

DIRETRA includes three modules: the parser, which outputs gloss sequences for the source language; the mapper, which transforms gloss sequences of the source language into those of the target language (TL); and the generator, which creates a representation in the target language. The system has been designed for Turkish; the next step is to implement other Turkic languages as well. The structure of the system is shown using the example of nominal inflection.

2. Morphological parsing

The first module of the system converts raw sequences of SL into gloss lines. The words are processed right-to-left: first all possible suffixes are found, then the remaining part is compared to the stem dictionary, cf. (Eryiğit / Adalı 2004). The parser can analyze morphology...

You are not authenticated to view the full text of this chapter or article.

This site requires a subscription or purchase to access the full text of books or journals.

Do you have any questions? Contact us.

Or login to access all content.