Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages
This work addresses the need for reliable and explainable translation for users not proficient in target languages, though it is incremental as it builds on existing confidence estimation techniques.
The paper tackles the problem of improving trustworthiness in machine translation for unfamiliar languages by proposing a direct, alignment-free source-side confidence estimation method that measures sensitivity of target word probabilities to source embedding changes, and it outperforms traditional alignment-based methods in detecting mistranslations.
We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing the user to intervene to correct mistranslations. However, confidence estimation in machine translation has traditionally focused on the target side. Whereas the conventional approach to source-side confidence estimation would have been to project target word probabilities to the source side via word alignments, we propose a direct, alignment-free approach that measures how sensitive the target word probabilities are to changes in the source embeddings. Experimental results show that our method outperforms traditional alignment-based methods at detection of mistranslations.