Evaluating Optimal Reference Translations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492698" target="_blank" >RIV/00216208:11320/24:10492698 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=C--Xjbsz9z" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=C--Xjbsz9z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1017/nlp.2024.3" target="_blank" >10.1017/nlp.2024.3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evaluating Optimal Reference Translations

Popis výsledku v původním jazyce

The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors and quality deficiencies that still persist. Furthermore, the quality of standard reference translations is commonly questioned and comparable quality levels have been reached by MT alone in several language pairs. Navigating further research in these high-resource settings is thus difficult. In this paper, we propose a methodology for creating more reliable document-level human reference translations, called &quot;optimal reference translations,&quot; with the simple aim to raise the bar of what should be deemed &quot;human translation quality.&quot; We evaluate the obtained document-level optimal reference translations in comparison with &quot;standard&quot; ones, confirming a significant quality increase and also documenting the relationship between evaluation and translation editing.

Název v anglickém jazyce

Evaluating Optimal Reference Translations

Popis výsledku anglicky

The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors and quality deficiencies that still persist. Furthermore, the quality of standard reference translations is commonly questioned and comparable quality levels have been reached by MT alone in several language pairs. Navigating further research in these high-resource settings is thus difficult. In this paper, we propose a methodology for creating more reliable document-level human reference translations, called &quot;optimal reference translations,&quot; with the simple aim to raise the bar of what should be deemed &quot;human translation quality.&quot; We evaluate the obtained document-level optimal reference translations in comparison with &quot;standard&quot; ones, confirming a significant quality increase and also documenting the relationship between evaluation and translation editing.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Natural language Processing (Cambridge)

ISSN

2977-0424

e-ISSN

2977-0424

Svazek periodika

2024

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

24

Strana od-do

1-24

Kód UT WoS článku

001327410600001

EID výsledku v databázi Scopus

—