Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475759" target="_blank" >RIV/00216208:11320/23:10475759 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2023.acl-long.122/" target="_blank" >https://aclanthology.org/2023.acl-long.122/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.acl-long.122" target="_blank" >10.18653/v1/2023.acl-long.122</a>

Result language

angličtina

Original language name

Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation

Original language description

We propose a genetic algorithm (GA) based method for modifying n-best lists produced by a machine translation (MT) system. Our method offers an innovative approach to improving MT quality and identifying weaknesses in evaluation metrics. Using common GA operations (mutation and crossover) on a list of hypotheses in combination with a fitness function (an arbitrary MT metric), we obtain novel and diverse outputs with high metric scores. With a combination of multiple MT metrics as the fitness function, the proposed method leads to an increase in translation quality as measured by other held-out automatic metrics.With a single metric (including popular ones such as COMET) as the fitness function, we find blind spots and flaws in the metric. This allows for an automated search for adversarial examples in an arbitrary metric, without prior assumptions on the form of such example. As a demonstration of the method, we create datasets of adversarial examples and use them to show that reference-free COMET is substantially less robust than the reference-based version.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

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

Publication year

2023

Confidentiality

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

Article name in the collection

Proceedings of 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

978-1-959429-72-2

ISSN

—

e-ISSN

—

Number of pages

22

Pages from-to

2191-2212

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Toronto, Canada

Event date

Jul 9, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—