A Fine-Grained Analysis of BERTScore

Result code in 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>

Result on the web

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

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

A Fine-Grained Analysis of BERTScore

Original language description

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

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

2021

Confidentiality

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

Article name in the collection

Proceedings of the Sixth Conference on Machine Translation

ISBN

978-1-954085-94-7

ISSN

—

e-ISSN

—

Number of pages

11

Pages from-to

507-517

Publisher name

Association for Computational Linguistics

Place of publication

Online

Event location

Online

Event date

Nov 10, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—