It's not a Non-Issue: Negation as a Source of Error in Machine Translation
This addresses a core linguistic challenge for machine translation users, though it is incremental as it focuses on a specific error source.
The study investigated whether negation causes errors in modern machine translation systems across 17 translation directions, finding that negation can reduce translation quality by over 60% in some cases.
As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We investigate whether translating negation is an issue for modern MT systems using 17 translation directions as test bed. Through thorough analysis, we find that indeed the presence of negation can significantly impact downstream quality, in some cases resulting in quality reductions of more than 60%. We also provide a linguistically motivated analysis that directly explains the majority of our findings. We release our annotations and code to replicate our analysis here: https://github.com/mosharafhossain/negation-mt.