Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492903" target="_blank" >RIV/00216208:11320/24:10492903 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2024.lrec-main.575/" target="_blank" >https://aclanthology.org/2024.lrec-main.575/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation

Original language description

Human evaluation is a critical component in machine translation system development and has received much attention in text translation research. However, little prior work exists on the topic of human evaluation for speech translation, which adds additional challenges such as noisy data and segmentation mismatches. We take the first steps to fill this gap by conducting a comprehensive human evaluation of the results of several shared tasks from the last International Workshop on Spoken Language Translation (IWSLT 2023). We propose an effective evaluation strategy based on automatic resegmentation and direct assessment with segment context. Our analysis revealed that: 1) the proposed evaluation strategy is robust and scores well-correlated with other types of human judgements; 2) automatic metrics are usually, but not always, well-correlated with direct assessment scores; and 3) COMET as a slightly stronger automatic metric than chrF, despite the segmentation noise introduced by the resegmentation step

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

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

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

Article name in the collection

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

ISBN

978-2-493-81410-4

ISSN

2522-2686

e-ISSN

—

Number of pages

12

Pages from-to

6484-6495

Publisher name

European Language Resources Association

Place of publication

Torino, Italy

Event location

Torino, Italy

Event date

May 22, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—