Source language classification of indirect translations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F22%3A10456674" target="_blank" >RIV/00216208:11210/22:10456674 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=SMT_u-XsKd" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=SMT_u-XsKd</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1075/target.00006.iva" target="_blank" >10.1075/target.00006.iva</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Source language classification of indirect translations

Popis výsledku v původním jazyce

One of the major barriers to the systematic study of indirect translation - that is, translations of translations - is the lack of efficient methods to identify these translations. In this article, we use supervised machine learning to examine whether computers can be harnessed to identify indirect translations. Our data consist of a monolingual comparable corpus that includes (1) nontranslated Finnish texts, (2) direct translations from English, French, German, Greek, and Swedish into Finnish, and (3) indirect translations from Greek (the ultimate source language) via English, French, German, and Swedish (mediating languages) into Finnish. We use n-grams of various types and lengths as feature sets and random forests as the statistical classification technique. To maximize the transferability of the method, the feature sets were implemented in accordance with the Universal Dependencies framework. This study confirms that computers can distinguish between translated and nontranslated Finnish, as well as between Finnish translations made from different source languages. Regarding indirect translations, the ultimate source language has a greater impact on the linguistic composition of indirect Finnish translations than their respective mediating languages. Hence, the indirect translations could not be reliably identified. Therefore, our results suggest that the reliable computational identification of indirect translations and their mediating languages requires a way to control for the effect of the ultimate source language.

Název v anglickém jazyce

Source language classification of indirect translations

Popis výsledku anglicky

One of the major barriers to the systematic study of indirect translation - that is, translations of translations - is the lack of efficient methods to identify these translations. In this article, we use supervised machine learning to examine whether computers can be harnessed to identify indirect translations. Our data consist of a monolingual comparable corpus that includes (1) nontranslated Finnish texts, (2) direct translations from English, French, German, Greek, and Swedish into Finnish, and (3) indirect translations from Greek (the ultimate source language) via English, French, German, and Swedish (mediating languages) into Finnish. We use n-grams of various types and lengths as feature sets and random forests as the statistical classification technique. To maximize the transferability of the method, the feature sets were implemented in accordance with the Universal Dependencies framework. This study confirms that computers can distinguish between translated and nontranslated Finnish, as well as between Finnish translations made from different source languages. Regarding indirect translations, the ultimate source language has a greater impact on the linguistic composition of indirect Finnish translations than their respective mediating languages. Hence, the indirect translations could not be reliably identified. Therefore, our results suggest that the reliable computational identification of indirect translations and their mediating languages requires a way to control for the effect of the ultimate source language.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

—

Návaznosti

—

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Target

ISSN

0924-1884

e-ISSN

1569-9986

Svazek periodika

34

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

25

Strana od-do

370-394

Kód UT WoS článku

000782566300001

EID výsledku v databázi Scopus

—