A Fine-Grained Analysis of BERTScore

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440537" target="_blank" >RIV/00216208:11320/21:10440537 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2021.wmt-1.59/" target="_blank" >https://aclanthology.org/2021.wmt-1.59/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A Fine-Grained Analysis of BERTScore

Popis výsledku v původním jazyce

BERTScore (Zhang et al., 2020), a recently proposed automatic metric for machine translation quality, uses BERT (Devlin et al., 2019), a large pre-trained language model to evaluate candidate translations with respect to a gold translation. Taking advantage of BERT&apos;s semantic and syntactic abilities, BERTScore seeks to avoid the flaws of earlier approaches like BLEU, instead scoring candidate translations based on their semantic similarity to the gold sentence. However, BERT is not infallible; while its performance on NLP tasks set a new state of the art in general, studies of specific syntactic and semantic phenomena have shown where BERT&apos;s performance deviates from that of humans more generally. This naturally raises the questions we address in this paper: what are the strengths and weaknesses of BERTScore? Do they relate to known weaknesses on the part of BERT? We find that while BERTScore can detect when a candidate differs from a reference in important content words, it is less sensitive to small

Název v anglickém jazyce

A Fine-Grained Analysis of BERTScore

Popis výsledku anglicky

BERTScore (Zhang et al., 2020), a recently proposed automatic metric for machine translation quality, uses BERT (Devlin et al., 2019), a large pre-trained language model to evaluate candidate translations with respect to a gold translation. Taking advantage of BERT&apos;s semantic and syntactic abilities, BERTScore seeks to avoid the flaws of earlier approaches like BLEU, instead scoring candidate translations based on their semantic similarity to the gold sentence. However, BERT is not infallible; while its performance on NLP tasks set a new state of the art in general, studies of specific syntactic and semantic phenomena have shown where BERT&apos;s performance deviates from that of humans more generally. This naturally raises the questions we address in this paper: what are the strengths and weaknesses of BERTScore? Do they relate to known weaknesses on the part of BERT? We find that while BERTScore can detect when a candidate differs from a reference in important content words, it is less sensitive to small

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 Sixth Conference on Machine Translation

ISBN

978-1-954085-94-7

ISSN

—

e-ISSN

—

Počet stran výsledku

11

Strana od-do

507-517

Název nakladatele

Association for Computational Linguistics

Místo vydání

Online

Místo konání akce

Online

Datum konání akce

10. 11. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—