SOURCE: SOURce-conditional elmo-style model for machine translation quality estimation

9Citations
Citations of this article
76Readers
Mendeley users who have this article in their library.

Abstract

Quality estimation (QE) of machine translation (MT) systems is a task of growing importance. It reduces the cost of post-editing, allowing machine-translated text to be used in formal occasions. In this work, we describe our submission system in WMT 2019 sentence-level QE task. We mainly explore the utilization of pre-trained translation models in QE and adopt a bi-directional translation-like strategy. The strategy is similar to ELMo, but additionally conditions on source sentences. Experiments on WMT QE dataset show that our strategy, which makes the pre-training slightly harder, can bring improvements for QE. In WMT-2019 QE task, our system ranked in the second place on En-De NMT dataset and the third place on En-Ru NMT dataset.

Cite

CITATION STYLE

APA

Zhou, J., Zhang, Z., & Hu, Z. (2019). SOURCE: SOURce-conditional elmo-style model for machine translation quality estimation. In WMT 2019 - 4th Conference on Machine Translation, Proceedings of the Conference (Vol. 3, pp. 106–111). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w19-5411

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free