TransQuest: Translation Quality Estimation with Cross-lingual Transformers

Tharindu Ranasinghe, Constantin Orasan, Ruslan Mitkov

    Research output: Chapter in Book/Published conference outputConference publication


    Recent years have seen big advances in the field of sentence-level quality estimation (QE), largely as a result of using neural-based architectures. However, the majority of these methods work only on the language pair they are trained on and need retraining for new language pairs. This process can prove difficult from a technical point of view and is usually computationally expensive. In this paper we propose a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. Our evaluation shows that the proposed methods achieve state-of-the-art results outperforming current open-source quality estimation frameworks when trained on datasets from WMT. In addition, the framework proves very useful in transfer learning settings, especially when dealing with low-resourced languages, allowing us to obtain very competitive results.
    Original languageEnglish
    Title of host publicationCOLING 2020: The 28th International Conference on Computational Linguistics
    Number of pages12
    Publication statusPublished - Dec 2020

    Bibliographical note

    ACL materials are Copyright © 1963–2023 ACL; Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.


    Dive into the research topics of 'TransQuest: Translation Quality Estimation with Cross-lingual Transformers'. Together they form a unique fingerprint.

    Cite this