Search Results for author:
Found 2 papers, 0 papers with code
Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation
We propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation.
Unsupervised Translation Quality Estimation Exploiting Synthetic Data and Pre-trained Multilingual Encoder
In this paper, we extensively investigate the usefulness of synthetic TQE data and pre-trained multilingual encoders in unsupervised sentence-level TQE, both of which have been proven effective in the supervised training scenarios.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
