Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation

Diptesh Kanojia, Marina Fomicheva, Tharindu Ranasinghe, Fred Blain, Constantin Orăsan, Lucia Specia

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

16 Downloads (Pure)

Abstract

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 meaning-preserving and meaning-altering perturbations is predictive of its overall performance, thus potentially allowing for comparing QE systems without relying on manual quality annotation.
Original languageEnglish
Title of host publicationProceedings of the Sixth Conference on Machine Translation
PublisherAssociation for Computational Linguistics (ACL)
Pages625-638
Number of pages14
ISBN (Print)978-1-954085-94-7
Publication statusPublished - 22 Sept 2021
Externally publishedYes

Keywords

  • cs.CL
  • cs.AI

Fingerprint

Dive into the research topics of 'Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation'. Together they form a unique fingerprint.

Cite this