Multi-view fusion for universal translation quality estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3APEVAZN2Q" target="_blank" >RIV/00216208:11320/23:PEVAZN2Q - isvavai.cz</a>

Výsledek na webu

<a href="https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1" target="_blank" >https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.inffus.2023.102022" target="_blank" >10.1016/j.inffus.2023.102022</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-view fusion for universal translation quality estimation

Popis výsledku v původním jazyce

"Machine translation quality estimation (QE) aims to evaluate the result of translation without reference. Despite the progress it has made, state-of-the-art QE models are proven to be biased. More specifically, they over-rely on spurious statistical features while ignoring the bilingual semantic adequacy, leading to performance degradation. Besides, existing approaches require large amounts of annotation data, restricting their applications in new domains and languages. In this work, we propose a universal framework for quality estimation based on multi-view fusion. We first introduce noise to the target side of the parallel sentence pair, either by pre-trained language model or by large language model. After that, with the clean parallel pairs and the noised pairs as different views, the QE model is trained to distinguish the clean pairs from the noised ones. Our method can improve the accuracy and generalizability in supervised scenario, and can solely perform estimation in zero-shot scenario. We perform experiments on WMT QE evaluation datasets under different scenarios, verifying the effectiveness of our method. We also make an in-depth investigation of the bias of QE model."

Název v anglickém jazyce

Multi-view fusion for universal translation quality estimation

Popis výsledku anglicky

"Machine translation quality estimation (QE) aims to evaluate the result of translation without reference. Despite the progress it has made, state-of-the-art QE models are proven to be biased. More specifically, they over-rely on spurious statistical features while ignoring the bilingual semantic adequacy, leading to performance degradation. Besides, existing approaches require large amounts of annotation data, restricting their applications in new domains and languages. In this work, we propose a universal framework for quality estimation based on multi-view fusion. We first introduce noise to the target side of the parallel sentence pair, either by pre-trained language model or by large language model. After that, with the clean parallel pairs and the noised pairs as different views, the QE model is trained to distinguish the clean pairs from the noised ones. Our method can improve the accuracy and generalizability in supervised scenario, and can solely perform estimation in zero-shot scenario. We perform experiments on WMT QE evaluation datasets under different scenarios, verifying the effectiveness of our method. We also make an in-depth investigation of the bias of QE model."

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

"INFORMATION FUSION"

ISSN

1566-2535

e-ISSN

—

Svazek periodika

102

Číslo periodika v rámci svazku

2024-2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

001083713100001

EID výsledku v databázi Scopus

—