SLTev: Comprehensive Evaluation of Spoken Language Translation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440518" target="_blank" >RIV/00216208:11320/21:10440518 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2021.eacl-demos.9" target="_blank" >https://aclanthology.org/2021.eacl-demos.9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2021.eacl-demos.9" target="_blank" >10.18653/v1/2021.eacl-demos.9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SLTev: Comprehensive Evaluation of Spoken Language Translation

Popis výsledku v původním jazyce

Automatic evaluation of Machine Translation(MT) quality has been investigated over several decades. Spoken Language Translation (SLT), especially when simultaneous, needs to consider additional criteria and does not have a standard evaluation procedure and a widely used toolkit. To fill the gap, we introduce SLTev, an open-source tool for assessing SLT in a comprehensive way. SLTev reports the quality, latency, and stability of an SLT candidate output based on the time-stamped transcript and reference translation into a target language. For quality, we rely on sacreBLEU which provides MT evaluation measures such as chrF or BLEU. For latency, we propose two new scoring techniques. For stability, we extend the previously defined measures with a normalized Flicker in our work. We also propose a new averaging of older measures. A preliminary version of SLTev was used in the IWSLT 2020 SHARED TASK. Moreover, a growing collection of test datasets directly accessible by SLTev are provided for system evaluati

Název v anglickém jazyce

SLTev: Comprehensive Evaluation of Spoken Language Translation

Popis výsledku anglicky

Automatic evaluation of Machine Translation(MT) quality has been investigated over several decades. Spoken Language Translation (SLT), especially when simultaneous, needs to consider additional criteria and does not have a standard evaluation procedure and a widely used toolkit. To fill the gap, we introduce SLTev, an open-source tool for assessing SLT in a comprehensive way. SLTev reports the quality, latency, and stability of an SLT candidate output based on the time-stamped transcript and reference translation into a target language. For quality, we rely on sacreBLEU which provides MT evaluation measures such as chrF or BLEU. For latency, we propose two new scoring techniques. For stability, we extend the previously defined measures with a normalized Flicker in our work. We also propose a new averaging of older measures. A preliminary version of SLTev was used in the IWSLT 2020 SHARED TASK. Moreover, a growing collection of test datasets directly accessible by SLTev are provided for system evaluati

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

ISBN

978-1-954085-05-3

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

71-79

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Online

Datum konání akce

19. 4. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—