| 1 |
Pushing the right buttons: adversarial evaluation of quality estimation
|
|
|
|
In: Proceedings of the Sixth Conference on Machine Translation ; 625 ; 638 (2022)
|
|
Abstract:
© (2021) The Authors. Published by Association for Computational Linguistics. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: https://aclanthology.org/2021.wmt-1.67 ; Current Machine Translation (MT) systems achieve very good results on a growing variety of language pairs and datasets. However, they are known to produce fluent translation outputs that can contain important meaning errors, thus undermining their reliability in practice. Quality Estimation (QE) is the task of automatically assessing the performance of MT systems at test time. Thus, in order to be useful, QE systems should be able to detect such errors. However, this ability is yet to be tested in the current evaluation practices, where QE systems are assessed only in terms of their correlation with human judgements. In this work, we bridge this gap by proposing a general methodology for adversarial testing of QE for MT. First, we show that despite a high correlation with human judgements achieved by the recent SOTA, certain types of meaning errors are still problematic for QE to detect. Second, we show that on average, the ability of a given model to discriminate between meaningpreserving and meaning-altering perturbations is predictive of its overall performance, thus potentially allowing for comparing QE systems without relying on manual quality annotation.
|
|
Keyword:
adversarial evaluation; machine translation; quality estimation
|
|
URL: http://hdl.handle.net/2436/624376
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Reverse racism: the construction of a slip narrative ; Racismo inverso: la construcción de una narrativa deslizante ; Racismo reverso: a construção de uma narrativa de esquiva
|
|
|
|
In: Signótica; Vol. 34 (2022) ; Signótica; v. 34 (2022) ; 2316-3690 ; 0103-7250 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
When Does Translation Require Context? A Data-driven, Multilingual Exploration ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Measuring and Increasing Context Usage in Context-Aware Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Do Context-Aware Translation Models Pay the Right Attention? ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Findings of the WMT 2021 Shared Task on Quality Estimation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Do Context-Aware Translation Models Pay the Right Attention? ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Findings of the WMT 2021 shared task on quality estimation
|
|
|
|
In: 689 ; 730 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Findings of the WMT 2020 shared task on quality estimation
|
|
|
|
In: 743 ; 764 (2020)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
MLQE-PE: A multilingual quality estimation and post-editing dataset
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
